Merge branch 'Automatica-3' of https://git.sibsci.ru/SergeyRevyakin/DroneDetector into Automatica-3

.dockerignore

@@ -1,17 +1,50 @@
-.git
-.vscode
-.venv-sdr
+# Default-deny: include only files required by Docker images.
+*
+
+!.dockerignore
+!deploy/
+!deploy/docker/
+!deploy/docker/**
+!deploy/requirements/
+!deploy/requirements/**
+!src/
+!src/**
+!common/
+!common/**
+!NN_server/
+!NN_server/**
+!telemetry/
+!telemetry/**
+!torchsig/
+!torchsig/**
+
+# Drop heavy or host-only artifacts even if their parent directory is included.
+.git/
+.vscode/
+.venv*/
 __pycache__/
 *.pyc
 *.pyo
-
-# Heavy host-only SDR sources
+*.tar
+*.tar.gz
+*.tgz
+*.zip
+*.iq
+logs/
+runtime/
+train_scripts/
+scripts_nn/
+orange_scripts/
+signal/
 gnuradio/
 gr-osmosdr/
 gr-osmosdr-0.2.6/
-
-# Local runtime artifacts
-NN_server/result/
-
-# Legacy install artifacts not needed in docker image
 install_scripts/
+NN_server/NN/
+NN_server/result/
+NN_server/__pycache__/
+src/__pycache__/
+common/__pycache__/
+telemetry/__pycache__/
+torchsig/__pycache__/
+torchsig/docs/

.env.example

@@ -1,272 +0,0 @@
-#################
-# GENERAL
-#################
-module_name=dronedetector
-freqs=433,750,868,915,1200,1500,2400,3300,4500,5200,5800
-
-signal_threshold=0.02
-signal_threshold_433=0.0195
-signal_threshold_700=0.01
-signal_threshold_868=0.01
-signal_threshold_5200=0.01
-signal_threshold_5800=0.01
-
-# Runtime flags
-# 1/0, true/false, yes/no, on/off
-debug_flag=0
-debug_freq_flag=0
-debug_module_flag=0
-send_to_module_flag=1
-save_data_flag=0
-freq_endpoint=process_data
-send_to_master_flag=1
-send_to_jammer_flag=0
-jammer_timeout=2
-master_timeout=1
-amount_connection_attempts=3
-mad_k_on=5.0
-mad_eps=0.05
-# Per-frequency MAD sensitivity (scanner frequencies)
-
-path_to_save_medians=/tmp/dronedetector/noises_medians/
-path_to_save_alarms=/tmp/dronedetector/alarms/
-elems_to_save=signal,abs_signal
-file_types_to_save=npy,npy
-smb_host=127.0.0.1
-smb_port=139
-smb_user=guest
-smb_pass=guest
-shared_folder=shared
-the_pc_name=dronedetector-host
-remote_pc_name=dronedetector-storage
-smb_domain=WORKGROUP
-
-#################
-# 433
-#################
-hack_433=
-c_freq_433=433
-f_step_433=-20e6
-f_bases_433=0.480e9
-f_roofs_433=0.400e9
-signal_length_433=1000000
-buffer_columns_size_433=11
-num_of_thinning_iter_433=32
-multiply_factor_433=1.3
-num_for_alarm_433=4
-mad_k_on_433=0
-dbfs_linear_offset_db_433=0
-dbfs_linear_abs_median_scale_433=0
-
-#################
-# 750
-#################
-hack_750=
-c_freq_750=750
-f_step_750=-20e6
-f_bases_750=0.755e9
-f_roofs_750=0.695e9
-signal_length_750=1000000
-buffer_columns_size_750=11
-num_of_thinning_iter_750=32
-multiply_factor_750=1.3
-num_for_alarm_750=4
-mad_k_on_750=0
-dbfs_linear_offset_db_750=0
-dbfs_linear_abs_median_scale_750=0
-
-
-#################
-# 915
-#################
-hack_915=
-c_freq_915=915
-f_step_915=-20e6
-f_bases_915=0.98e9
-f_roofs_915=0.840e9
-signal_length_915=1000000
-buffer_columns_size_915=11
-num_of_thinning_iter_915=32
-multiply_factor_915=1.3
-num_for_alarm_915=4
-mad_k_on_915=0
-dbfs_linear_offset_db_915=0
-dbfs_linear_abs_median_scale_915=0
-
-#################
-# 1200
-#################
-hack_1200=
-c_freq_1200=1200
-f_step_1200=-20e6
-f_bases_1200=1.1e9
-f_roofs_1200=1.3e9
-signal_length_1200=1000000
-buffer_columns_size_1200=11
-num_of_thinning_iter_1200=32
-multiply_factor_1200=1.3
-num_for_alarm_1200=4
-mad_k_on_1200=0
-dbfs_linear_offset_db_1200=0
-dbfs_linear_abs_median_scale_1200=0
-
-
-#################
-# 1500
-#################
-hack_1500=
-c_freq_1500=1500
-f_step_1500=-20e6
-f_bases_1500=1.605e9
-f_roofs_1500=1.405e9
-signal_length_1500=1000000
-buffer_columns_size_1500=11
-num_of_thinning_iter_1500=32
-multiply_factor_1500=1.3
-num_for_alarm_1500=4
-mad_k_on_1500=0
-dbfs_linear_offset_db_1500=0
-dbfs_linear_abs_median_scale_1500=0
-
-
-#################
-# 2400
-#################
-hack_2400=
-c_freq_2400=2400
-f_step_2400=-20e6
-f_bases_2400=2.3e9
-f_roofs_2400=2.5e9
-signal_length_2400=1000000
-buffer_columns_size_2400=11
-num_of_thinning_iter_2400=32
-multiply_factor_2400=1.3
-num_for_alarm_2400=4
-mad_k_on_2400=0
-dbfs_linear_offset_db_2400=0
-dbfs_linear_abs_median_scale_2400=0
-
-#################
-# 3300
-#################
-hack_3300=
-c_freq_3300=3300
-f_step_3300=-20e6
-f_bases_3300=3.5e9
-f_roofs_3300=3.3e9
-signal_length_3300=1000000
-buffer_columns_size_3300=11
-num_of_thinning_iter_3300=32
-multiply_factor_3300=1.3
-num_for_alarm_3300=3
-mad_k_on_3300=0
-dbfs_linear_offset_db_3300=0
-dbfs_linear_abs_median_scale_3300=0
-
-#################
-# 4500
-#################
-hack_4500=
-c_freq_4500=4500
-f_step_4500=-20e6
-f_bases_4500=4.7e9
-f_roofs_4500=4.5e9
-signal_length_4500=1000000
-buffer_columns_size_4500=11
-num_of_thinning_iter_4500=32
-multiply_factor_4500=1.3
-num_for_alarm_4500=2
-mad_k_on_4500=0
-dbfs_linear_offset_db_4500=0
-dbfs_linear_abs_median_scale_4500=0
-
-
-#################
-# 5200
-#################
-hack_5200=
-c_freq_5200=5200
-f_step_5200=-20e6
-f_bases_5200=5.3e9
-f_roofs_5200=5.1e9
-signal_length_5200=1000000
-buffer_columns_size_5200=11
-num_of_thinning_iter_5200=32
-multiply_factor_5200=1.08
-num_for_alarm_5200=3
-mad_k_on_5200=0
-dbfs_linear_offset_db_5200=0
-dbfs_linear_abs_median_scale_4500=0
-
-#################
-# 5800
-#################
-hack_5800=
-c_freq_5800=5800
-f_step_5800=-20e6
-f_bases_5800=5.8e9
-f_roofs_5800=5.5e9
-signal_length_5800=1000000
-buffer_columns_size_5800=11
-num_of_thinning_iter_5800=32
-multiply_factor_5800=1.08
-num_for_alarm_5800=3
-mad_k_on_5800=0
-dbfs_linear_offset_db_5200=0
-dbfs_linear_abs_median_scale_5800=0
-
-
-#################
-# MODULE SERVER (server_to_master)
-#################
-lochost=0.0.0.0
-locport=5010
-master_server_ip=192.168.11.223
-master_server_port=3000
-module_mac=bc:fc:e7:ca:87:2b
-module_ip=192.168.11.223
-threshold_to_alarm=5
-num_of_clear_packs=5
-time_to_jam=30
-time_to_fresh=5
-active_interval_to_send=1
-passive_interval_to_send=60
-gpsport=/dev/null
-latitude=1
-longitude=1
-jamhost=127.0.0.1
-jamport=3000
-
-#################
-# ORANGE SDR (915/1200/2400 -> NN_server)
-#################
-POROG_2400=0.01
-HACKID_2400=
-POROG_1200=0.01
-HACKID_1200=
-POROG_915=0.01
-HACKID_915=
-SERVER_IP_1=127.0.0.1
-SERVER_PORT_1=8080
-SERVER_IP_2=127.0.0.1
-SERVER_PORT_2=8080
-
-#################
-# NN_SERVER
-#################
-FREQS=915,1200,2400
-PATH_TO_NN=/app/NN_server/NN/
-SRC_RESULT=/app/NN_server/result/
-SRC_EXAMPLE=${PATH_TO_NN}example/
-
-NN_1='${PATH_TO_NN}resnet18_1.pth && ${PATH_TO_NN}config_resnet18.yaml && ${SRC_EXAMPLE} && ${SRC_RESULT} && Resnet18_1_2400 && build_func_resnet18 && pre_func_resnet18 && inference_func_resnet18 && post_func_resnet18 && [drone,noise,wifi] && 10 && 1 && /app/NN_server/datasets/full_dataset_pic/'
-NN_21='${PATH_TO_NN}ensemble_1.2.pth && ${PATH_TO_NN}config_ensemble.yaml && ${SRC_EXAMPLE} && ${SRC_RESULT} && ensemble_1200 && build_func_ensemble && pre_func_ensemble && inference_func_ensemble && post_func_ensemble && [drone,noise] && 10 && 1 && /app/NN_server/datasets/full_dataset/'
-NN_22='${PATH_TO_NN}ensemble_915.pth && ${PATH_TO_NN}config_ensemble.yaml && ${SRC_EXAMPLE} && ${SRC_RESULT} && ensemble_915 && build_func_ensemble && pre_func_ensemble && inference_func_ensemble && post_func_ensemble && [drone,noise] && 10 && 1 && /app/NN_server/datasets/full_dataset/'
-
-GENERAL_SERVER_IP=dronedetector-server-to-master
-GENERAL_SERVER_PORT=5010
-SERVER_IP=0.0.0.0
-SERVER_PORT=8080
-
-NN_HOT_RELOAD=1
-

.gitignore

@@ -144,10 +144,9 @@ celerybeat.pid
 
 # Environments
 .env
-.env.bak*
 .venv
 env/
-.venv/
+venv/
 ENV/
 env.bak/
 venv.bak/
@@ -189,9 +188,7 @@ runtime/
 
 /.venv-*/*
 
-/models/ensemble_*/
+/train_scripts/models
 
-NN_server/server.py.bak_streak_gate
-
-*.npy
-train_scripts/models/ensemble*/
+logs/nn_results_*.csv
+.codex

.venv-sdr/bin/Activate.ps1

@@ -0,0 +1,247 @@
+<#
+.Synopsis
+Activate a Python virtual environment for the current PowerShell session.
+
+.Description
+Pushes the python executable for a virtual environment to the front of the
+$Env:PATH environment variable and sets the prompt to signify that you are
+in a Python virtual environment. Makes use of the command line switches as
+well as the `pyvenv.cfg` file values present in the virtual environment.
+
+.Parameter VenvDir
+Path to the directory that contains the virtual environment to activate. The
+default value for this is the parent of the directory that the Activate.ps1
+script is located within.
+
+.Parameter Prompt
+The prompt prefix to display when this virtual environment is activated. By
+default, this prompt is the name of the virtual environment folder (VenvDir)
+surrounded by parentheses and followed by a single space (ie. '(.venv) ').
+
+.Example
+Activate.ps1
+Activates the Python virtual environment that contains the Activate.ps1 script.
+
+.Example
+Activate.ps1 -Verbose
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and shows extra information about the activation as it executes.
+
+.Example
+Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
+Activates the Python virtual environment located in the specified location.
+
+.Example
+Activate.ps1 -Prompt "MyPython"
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and prefixes the current prompt with the specified string (surrounded in
+parentheses) while the virtual environment is active.
+
+.Notes
+On Windows, it may be required to enable this Activate.ps1 script by setting the
+execution policy for the user. You can do this by issuing the following PowerShell
+command:
+
+PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
+
+For more information on Execution Policies: 
+https://go.microsoft.com/fwlink/?LinkID=135170
+
+#>
+Param(
+    [Parameter(Mandatory = $false)]
+    [String]
+    $VenvDir,
+    [Parameter(Mandatory = $false)]
+    [String]
+    $Prompt
+)
+
+<# Function declarations --------------------------------------------------- #>
+
+<#
+.Synopsis
+Remove all shell session elements added by the Activate script, including the
+addition of the virtual environment's Python executable from the beginning of
+the PATH variable.
+
+.Parameter NonDestructive
+If present, do not remove this function from the global namespace for the
+session.
+
+#>
+function global:deactivate ([switch]$NonDestructive) {
+    # Revert to original values
+
+    # The prior prompt:
+    if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
+        Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
+        Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
+    }
+
+    # The prior PYTHONHOME:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
+        Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
+    }
+
+    # The prior PATH:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
+        Remove-Item -Path Env:_OLD_VIRTUAL_PATH
+    }
+
+    # Just remove the VIRTUAL_ENV altogether:
+    if (Test-Path -Path Env:VIRTUAL_ENV) {
+        Remove-Item -Path env:VIRTUAL_ENV
+    }
+
+    # Just remove VIRTUAL_ENV_PROMPT altogether.
+    if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
+        Remove-Item -Path env:VIRTUAL_ENV_PROMPT
+    }
+
+    # Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
+    if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
+        Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
+    }
+
+    # Leave deactivate function in the global namespace if requested:
+    if (-not $NonDestructive) {
+        Remove-Item -Path function:deactivate
+    }
+}
+
+<#
+.Description
+Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
+given folder, and returns them in a map.
+
+For each line in the pyvenv.cfg file, if that line can be parsed into exactly
+two strings separated by `=` (with any amount of whitespace surrounding the =)
+then it is considered a `key = value` line. The left hand string is the key,
+the right hand is the value.
+
+If the value starts with a `'` or a `"` then the first and last character is
+stripped from the value before being captured.
+
+.Parameter ConfigDir
+Path to the directory that contains the `pyvenv.cfg` file.
+#>
+function Get-PyVenvConfig(
+    [String]
+    $ConfigDir
+) {
+    Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
+
+    # Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
+    $pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
+
+    # An empty map will be returned if no config file is found.
+    $pyvenvConfig = @{ }
+
+    if ($pyvenvConfigPath) {
+
+        Write-Verbose "File exists, parse `key = value` lines"
+        $pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
+
+        $pyvenvConfigContent | ForEach-Object {
+            $keyval = $PSItem -split "\s*=\s*", 2
+            if ($keyval[0] -and $keyval[1]) {
+                $val = $keyval[1]
+
+                # Remove extraneous quotations around a string value.
+                if ("'""".Contains($val.Substring(0, 1))) {
+                    $val = $val.Substring(1, $val.Length - 2)
+                }
+
+                $pyvenvConfig[$keyval[0]] = $val
+                Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
+            }
+        }
+    }
+    return $pyvenvConfig
+}
+
+
+<# Begin Activate script --------------------------------------------------- #>
+
+# Determine the containing directory of this script
+$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
+$VenvExecDir = Get-Item -Path $VenvExecPath
+
+Write-Verbose "Activation script is located in path: '$VenvExecPath'"
+Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
+Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
+
+# Set values required in priority: CmdLine, ConfigFile, Default
+# First, get the location of the virtual environment, it might not be
+# VenvExecDir if specified on the command line.
+if ($VenvDir) {
+    Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
+}
+else {
+    Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
+    $VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
+    Write-Verbose "VenvDir=$VenvDir"
+}
+
+# Next, read the `pyvenv.cfg` file to determine any required value such
+# as `prompt`.
+$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
+
+# Next, set the prompt from the command line, or the config file, or
+# just use the name of the virtual environment folder.
+if ($Prompt) {
+    Write-Verbose "Prompt specified as argument, using '$Prompt'"
+}
+else {
+    Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
+    if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
+        Write-Verbose "  Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
+        $Prompt = $pyvenvCfg['prompt'];
+    }
+    else {
+        Write-Verbose "  Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
+        Write-Verbose "  Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
+        $Prompt = Split-Path -Path $venvDir -Leaf
+    }
+}
+
+Write-Verbose "Prompt = '$Prompt'"
+Write-Verbose "VenvDir='$VenvDir'"
+
+# Deactivate any currently active virtual environment, but leave the
+# deactivate function in place.
+deactivate -nondestructive
+
+# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
+# that there is an activated venv.
+$env:VIRTUAL_ENV = $VenvDir
+
+if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
+
+    Write-Verbose "Setting prompt to '$Prompt'"
+
+    # Set the prompt to include the env name
+    # Make sure _OLD_VIRTUAL_PROMPT is global
+    function global:_OLD_VIRTUAL_PROMPT { "" }
+    Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
+    New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
+
+    function global:prompt {
+        Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
+        _OLD_VIRTUAL_PROMPT
+    }
+    $env:VIRTUAL_ENV_PROMPT = $Prompt
+}
+
+# Clear PYTHONHOME
+if (Test-Path -Path Env:PYTHONHOME) {
+    Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
+    Remove-Item -Path Env:PYTHONHOME
+}
+
+# Add the venv to the PATH
+Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
+$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

.venv-sdr/bin/activate

@@ -0,0 +1,70 @@
+# This file must be used with "source bin/activate" *from bash*
+# You cannot run it directly
+
+deactivate () {
+    # reset old environment variables
+    if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
+        PATH="${_OLD_VIRTUAL_PATH:-}"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
+        PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # Call hash to forget past commands. Without forgetting
+    # past commands the $PATH changes we made may not be respected
+    hash -r 2> /dev/null
+
+    if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
+        PS1="${_OLD_VIRTUAL_PS1:-}"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    unset VIRTUAL_ENV_PROMPT
+    if [ ! "${1:-}" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+# on Windows, a path can contain colons and backslashes and has to be converted:
+if [ "${OSTYPE:-}" = "cygwin" ] || [ "${OSTYPE:-}" = "msys" ] ; then
+    # transform D:\path\to\venv to /d/path/to/venv on MSYS
+    # and to /cygdrive/d/path/to/venv on Cygwin
+    export VIRTUAL_ENV=$(cygpath /home/sibscience-4/from_ssh/DroneDetector/.venv-sdr)
+else
+    # use the path as-is
+    export VIRTUAL_ENV=/home/sibscience-4/from_ssh/DroneDetector/.venv-sdr
+fi
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/"bin":$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
+# could use `if (set -u; : $PYTHONHOME) ;` in bash
+if [ -n "${PYTHONHOME:-}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1:-}"
+    PS1='(.venv-sdr) '"${PS1:-}"
+    export PS1
+    VIRTUAL_ENV_PROMPT='(.venv-sdr) '
+    export VIRTUAL_ENV_PROMPT
+fi
+
+# Call hash to forget past commands. Without forgetting
+# past commands the $PATH changes we made may not be respected
+hash -r 2> /dev/null

.venv-sdr/bin/activate.csh

@@ -0,0 +1,27 @@
+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+
+# Created by Davide Di Blasi <davidedb@gmail.com>.
+# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV /home/sibscience-4/from_ssh/DroneDetector/.venv-sdr
+
+set _OLD_VIRTUAL_PATH="$PATH"
+setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
+
+
+set _OLD_VIRTUAL_PROMPT="$prompt"
+
+if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
+    set prompt = '(.venv-sdr) '"$prompt"
+    setenv VIRTUAL_ENV_PROMPT '(.venv-sdr) '
+endif
+
+alias pydoc python -m pydoc
+
+rehash

.venv-sdr/bin/activate.fish

@@ -0,0 +1,69 @@
+# This file must be used with "source <venv>/bin/activate.fish" *from fish*
+# (https://fishshell.com/). You cannot run it directly.
+
+function deactivate  -d "Exit virtual environment and return to normal shell environment"
+    # reset old environment variables
+    if test -n "$_OLD_VIRTUAL_PATH"
+        set -gx PATH $_OLD_VIRTUAL_PATH
+        set -e _OLD_VIRTUAL_PATH
+    end
+    if test -n "$_OLD_VIRTUAL_PYTHONHOME"
+        set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
+        set -e _OLD_VIRTUAL_PYTHONHOME
+    end
+
+    if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
+        set -e _OLD_FISH_PROMPT_OVERRIDE
+        # prevents error when using nested fish instances (Issue #93858)
+        if functions -q _old_fish_prompt
+            functions -e fish_prompt
+            functions -c _old_fish_prompt fish_prompt
+            functions -e _old_fish_prompt
+        end
+    end
+
+    set -e VIRTUAL_ENV
+    set -e VIRTUAL_ENV_PROMPT
+    if test "$argv[1]" != "nondestructive"
+        # Self-destruct!
+        functions -e deactivate
+    end
+end
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+set -gx VIRTUAL_ENV /home/sibscience-4/from_ssh/DroneDetector/.venv-sdr
+
+set -gx _OLD_VIRTUAL_PATH $PATH
+set -gx PATH "$VIRTUAL_ENV/"bin $PATH
+
+# Unset PYTHONHOME if set.
+if set -q PYTHONHOME
+    set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
+    set -e PYTHONHOME
+end
+
+if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
+    # fish uses a function instead of an env var to generate the prompt.
+
+    # Save the current fish_prompt function as the function _old_fish_prompt.
+    functions -c fish_prompt _old_fish_prompt
+
+    # With the original prompt function renamed, we can override with our own.
+    function fish_prompt
+        # Save the return status of the last command.
+        set -l old_status $status
+
+        # Output the venv prompt; color taken from the blue of the Python logo.
+        printf "%s%s%s" (set_color 4B8BBE) '(.venv-sdr) ' (set_color normal)
+
+        # Restore the return status of the previous command.
+        echo "exit $old_status" | .
+        # Output the original/"old" prompt.
+        _old_fish_prompt
+    end
+
+    set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
+    set -gx VIRTUAL_ENV_PROMPT '(.venv-sdr) '
+end

.venv-sdr/bin/f2py

@@ -0,0 +1,6 @@
+#!/home/sibscience-4/from_ssh/DroneDetector/.venv-sdr/bin/python3
+import sys
+from numpy.f2py.f2py2e import main
+if __name__ == '__main__':
+    sys.argv[0] = sys.argv[0].removesuffix('.exe')
+    sys.exit(main())

.venv-sdr/bin/normalizer

@@ -0,0 +1,6 @@
+#!/home/sibscience-4/from_ssh/DroneDetector/.venv-sdr/bin/python3
+import sys
+from charset_normalizer.cli import cli_detect
+if __name__ == '__main__':
+    sys.argv[0] = sys.argv[0].removesuffix('.exe')
+    sys.exit(cli_detect())

.venv-sdr/bin/pip

@@ -0,0 +1,8 @@
+#!/home/sibscience-4/from_ssh/DroneDetector/.venv-sdr/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

.venv-sdr/bin/pip3

@@ -0,0 +1,8 @@
+#!/home/sibscience-4/from_ssh/DroneDetector/.venv-sdr/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

.venv-sdr/bin/pip3.12

@@ -0,0 +1,8 @@
+#!/home/sibscience-4/from_ssh/DroneDetector/.venv-sdr/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

.venv-sdr/bin/python

@@ -0,0 +1 @@
+python3

.venv-sdr/bin/python3

@@ -0,0 +1 @@
+/usr/bin/python3

.venv-sdr/bin/python3.12

@@ -0,0 +1 @@
+python3

.venv-sdr/lib64

@@ -0,0 +1 @@
+lib

.venv-sdr/pyvenv.cfg

@@ -0,0 +1,5 @@
+home = /usr/bin
+include-system-site-packages = true
+version = 3.12.3
+executable = /usr/bin/python3.12
+command = /usr/bin/python3 -m venv --system-site-packages /home/sibscience-4/from_ssh/DroneDetector/.venv-sdr

CLAUDE.md

@@ -1,66 +0,0 @@
-
-# CLAUDE.md
-
-Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
-
-**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
-
-## 1. Think Before Coding
-
-**Don't assume. Don't hide confusion. Surface tradeoffs.**
-
-Before implementing:
-- State your assumptions explicitly. If uncertain, ask.
-- If multiple interpretations exist, present them - don't pick silently.
-- If a simpler approach exists, say so. Push back when warranted.
-- If something is unclear, stop. Name what's confusing. Ask.
-
-## 2. Simplicity First
-
-**Minimum code that solves the problem. Nothing speculative.**
-
-- No features beyond what was asked.
-- No abstractions for single-use code.
-- No "flexibility" or "configurability" that wasn't requested.
-- No error handling for impossible scenarios.
-- If you write 200 lines and it could be 50, rewrite it.
-
-Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
-
-## 3. Surgical Changes
-
-**Touch only what you must. Clean up only your own mess.**
-
-When editing existing code:
-- Don't "improve" adjacent code, comments, or formatting.
-- Don't refactor things that aren't broken.
-- Match existing style, even if you'd do it differently.
-- If you notice unrelated dead code, mention it - don't delete it.
-
-When your changes create orphans:
-- Remove imports/variables/functions that YOUR changes made unused.
-- Don't remove pre-existing dead code unless asked.
-
-The test: Every changed line should trace directly to the user's request.
-
-## 4. Goal-Driven Execution
-
-**Define success criteria. Loop until verified.**
-
-Transform tasks into verifiable goals:
-- "Add validation" → "Write tests for invalid inputs, then make them pass"
-- "Fix the bug" → "Write a test that reproduces it, then make it pass"
-- "Refactor X" → "Ensure tests pass before and after"
-
-For multi-step tasks, state a brief plan:
-```
-1. [Step] → verify: [check]
-2. [Step] → verify: [check]
-3. [Step] → verify: [check]
-```
-
-Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
-
----
-
-**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

NN_server/Model.py

@@ -154,18 +154,22 @@ class Model(object):
         except Exception as exc:
             print(str(exc))
 
-    def _prepare_data(self, data=None):
+    def _prepare_data(self, data=None, ind_inference=None):
         try:
+            if ind_inference is None:
+                ind_inference = Model.get_ind_inference()
             print('Подготовка данных' + self._shablon)
-            self._data = self._pre_func(data, src=self._src_result, ind_inference=Model.get_ind_inference())
+            self._data = self._pre_func(data, src=self._src_result, ind_inference=ind_inference)
         except Exception as exc:
             print(str(exc))
 
-    def _post_data(self, prediction=None):
+    def _post_data(self, prediction=None, ind_inference=None):
+        if ind_inference is None:
+            ind_inference = Model.get_ind_inference()
         print('Постобработка данных' + self._shablon)
         self._ind_inference += 1
         self._post_func(src=self._src_result, data=self._data, model_id=self._model_id, model_type=self._type_model,
-                        ind_inference=Model.get_ind_inference(), prediction=prediction)
+                        ind_inference=ind_inference, prediction=prediction)
 
     def get_test_inference(self):
         try:
@@ -248,22 +252,25 @@ class Model(object):
         except Exception as exc:
             print(str(exc))
 
-    def get_inference(self, data=None):
+    def get_inference(self, data=None, ind_inference=None):
         try:
-            return self._inference(data=data)
+            return self._inference(data=data, ind_inference=ind_inference)
         except Exception as exc:
             print(str(exc))
             return None
 
-    def _inference(self, data=None):
+    def _inference(self, data=None, ind_inference=None):
         try:
-            Model._add_in_result_list(type_model=self._type_model, ind_inference=self.get_ind_inference(), list_to_add=[])
-            self._prepare_data(data=data)
+            if ind_inference is None:
+                ind_inference = Model.get_ind_inference()
+            Model._add_in_result_list(type_model=self._type_model, ind_inference=ind_inference, list_to_add=[])
+            self._prepare_data(data=data, ind_inference=ind_inference)
             print('Инференс' + self._shablon)
             prediction, probability = self._inference_func(data=self._data, model=self._model, mapping=self._classes,
                                                            shablon=self._shablon)
-            Model._add_in_result_list(type_model=self._type_model, ind_inference=self.get_ind_inference(), list_to_add=[prediction, probability])
-            self._post_data(prediction=prediction)
+            print('RESULT' + self._shablon + ': ' + str(prediction) + ' (probability=' + str(probability) + ')')
+            Model._add_in_result_list(type_model=self._type_model, ind_inference=ind_inference, list_to_add=[prediction, probability])
+            self._post_data(prediction=prediction, ind_inference=ind_inference)
 
             gc.collect()
             return prediction, probability

NN_server/Models/ensemble_1200_v44.py

@@ -6,9 +6,11 @@ import torch
 import cv2
 import gc
 import io
+import os
+import re
 
 
-def _render_plot(values, figsize=(16, 16), dpi=16):
+def _render_signal_channel(values, figsize=(16, 16), dpi=16, resize=(256, 256)):
     import matplotlib.pyplot as plt
 
     fig = plt.figure(figsize=figsize)
@@ -28,6 +30,34 @@ def _render_plot(values, figsize=(16, 16), dpi=16):
     if img is None:
         raise RuntimeError("failed to decode plot image")
 
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    if resize is not None:
+        img = cv2.resize(img, resize)
+
+    plt.clf()
+    plt.cla()
+    plt.close()
+    plt.close(fig)
+
+    return img
+
+
+def _render_training_png(image):
+    import matplotlib.pyplot as plt
+
+    fig = plt.figure()
+    plt.imshow(image)
+
+    buf = io.BytesIO()
+    fig.savefig(buf, format="png")
+    buf.seek(0)
+    img_arr = np.frombuffer(buf.getvalue(), dtype=np.uint8)
+    buf.close()
+
+    img = cv2.imdecode(img_arr, 1)
+    if img is None:
+        raise RuntimeError("failed to decode training-style image")
+
     plt.clf()
     plt.cla()
     plt.close()
@@ -36,6 +66,42 @@ def _render_plot(values, figsize=(16, 16), dpi=16):
     return np.asarray(cv2.split(img), dtype=np.float32)
 
 
+def _prune_old_inference_images(src, model_type, model_id, keep_last=200):
+    try:
+        keep_last = int(os.getenv("INFERENCE_IMAGE_KEEP_LAST", str(keep_last)))
+    except ValueError:
+        keep_last = keep_last
+
+    if keep_last <= 0 or not src or not os.path.isdir(src):
+        return
+
+    pattern = re.compile(
+        r"_inference_(\d+)_.*_"
+        + re.escape(str(model_id))
+        + "_"
+        + re.escape(str(model_type))
+        + r"\.png$"
+    )
+    grouped = {}
+    for name in os.listdir(src):
+        match = pattern.match(name)
+        if match is None:
+            continue
+        grouped.setdefault(int(match.group(1)), []).append(name)
+
+    if len(grouped) <= keep_last:
+        return
+
+    for old_result_id in sorted(grouped)[: len(grouped) - keep_last]:
+        for name in grouped[old_result_id]:
+            try:
+                os.remove(os.path.join(src, name))
+            except FileNotFoundError:
+                pass
+            except OSError as exc:
+                print(f"failed to remove old inference image {name}: {exc}")
+
+
 def pre_func_ensemble(data=None, src="", ind_inference=0):
     try:
         import matplotlib.pyplot as plt
@@ -47,8 +113,8 @@ def pre_func_ensemble(data=None, src="", ind_inference=0):
         imag = np.asarray(data[1], dtype=np.float32)
         signal = real + 1j * imag
 
-        img_real = _render_plot(signal.real)
-        img_mag = _render_plot(np.abs(signal))
+        img_real = _render_training_png(_render_signal_channel(signal.real))
+        img_mag = _render_training_png(_render_signal_channel(np.abs(signal)))
 
         cv2.destroyAllWindows()
         gc.collect()
@@ -164,7 +230,7 @@ def post_func_ensemble(src="", model_type="", prediction="", model_id=0, ind_inf
         matplotlib.use("Agg")
         plt.ioff()
 
-        if int(ind_inference) <= 100 and isinstance(data, (list, tuple)) and len(data) >= 2:
+        if isinstance(data, (list, tuple)) and len(data) >= 2:
             fig, ax = plt.subplots()
             ax.imshow(np.moveaxis(data[0], 0, -1))
             plt.savefig(src + "_inference_" + str(ind_inference) + "_" + prediction + "_real_" + str(model_id) + "_" + model_type + ".png")
@@ -183,6 +249,8 @@ def post_func_ensemble(src="", model_type="", prediction="", model_id=0, ind_inf
             cv2.destroyAllWindows()
             gc.collect()
 
+            _prune_old_inference_images(src, model_type, model_id)
+
         plt.clf()
         plt.cla()
         plt.close()

NN_server/Models/ensemble_2400_v44.py

@@ -6,9 +6,11 @@ import torch
 import cv2
 import gc
 import io
+import os
+import re
 
 
-def _render_plot(values, figsize=(16, 16), dpi=16):
+def _render_signal_channel(values, figsize=(16, 16), dpi=16, resize=(256, 256)):
     import matplotlib.pyplot as plt
 
     fig = plt.figure(figsize=figsize)
@@ -28,6 +30,34 @@ def _render_plot(values, figsize=(16, 16), dpi=16):
     if img is None:
         raise RuntimeError("failed to decode plot image")
 
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    if resize is not None:
+        img = cv2.resize(img, resize)
+
+    plt.clf()
+    plt.cla()
+    plt.close()
+    plt.close(fig)
+
+    return img
+
+
+def _render_training_png(image):
+    import matplotlib.pyplot as plt
+
+    fig = plt.figure()
+    plt.imshow(image)
+
+    buf = io.BytesIO()
+    fig.savefig(buf, format="png")
+    buf.seek(0)
+    img_arr = np.frombuffer(buf.getvalue(), dtype=np.uint8)
+    buf.close()
+
+    img = cv2.imdecode(img_arr, 1)
+    if img is None:
+        raise RuntimeError("failed to decode training-style image")
+
     plt.clf()
     plt.cla()
     plt.close()
@@ -36,6 +66,42 @@ def _render_plot(values, figsize=(16, 16), dpi=16):
     return np.asarray(cv2.split(img), dtype=np.float32)
 
 
+def _prune_old_inference_images(src, model_type, model_id, keep_last=200):
+    try:
+        keep_last = int(os.getenv("INFERENCE_IMAGE_KEEP_LAST", str(keep_last)))
+    except ValueError:
+        keep_last = keep_last
+
+    if keep_last <= 0 or not src or not os.path.isdir(src):
+        return
+
+    pattern = re.compile(
+        r"_inference_(\d+)_.*_"
+        + re.escape(str(model_id))
+        + "_"
+        + re.escape(str(model_type))
+        + r"\.png$"
+    )
+    grouped = {}
+    for name in os.listdir(src):
+        match = pattern.match(name)
+        if match is None:
+            continue
+        grouped.setdefault(int(match.group(1)), []).append(name)
+
+    if len(grouped) <= keep_last:
+        return
+
+    for old_result_id in sorted(grouped)[: len(grouped) - keep_last]:
+        for name in grouped[old_result_id]:
+            try:
+                os.remove(os.path.join(src, name))
+            except FileNotFoundError:
+                pass
+            except OSError as exc:
+                print(f"failed to remove old inference image {name}: {exc}")
+
+
 def pre_func_ensemble(data=None, src="", ind_inference=0):
     try:
         import matplotlib.pyplot as plt
@@ -47,8 +113,8 @@ def pre_func_ensemble(data=None, src="", ind_inference=0):
         imag = np.asarray(data[1], dtype=np.float32)
         signal = real + 1j * imag
 
-        img_real = _render_plot(signal.real)
-        img_mag = _render_plot(np.abs(signal))
+        img_real = _render_training_png(_render_signal_channel(signal.real))
+        img_mag = _render_training_png(_render_signal_channel(np.abs(signal)))
 
         cv2.destroyAllWindows()
         gc.collect()
@@ -164,7 +230,7 @@ def post_func_ensemble(src="", model_type="", prediction="", model_id=0, ind_inf
         matplotlib.use("Agg")
         plt.ioff()
 
-        if int(ind_inference) <= 100 and isinstance(data, (list, tuple)) and len(data) >= 2:
+        if isinstance(data, (list, tuple)) and len(data) >= 2:
             fig, ax = plt.subplots()
             ax.imshow(np.moveaxis(data[0], 0, -1))
             plt.savefig(src + "_inference_" + str(ind_inference) + "_" + prediction + "_real_" + str(model_id) + "_" + model_type + ".png")
@@ -183,6 +249,8 @@ def post_func_ensemble(src="", model_type="", prediction="", model_id=0, ind_inf
             cv2.destroyAllWindows()
             gc.collect()
 
+            _prune_old_inference_images(src, model_type, model_id)
+
         plt.clf()
         plt.cla()
         plt.close()

NN_server/Models/ensemble_915_v44.py

@@ -1,197 +0,0 @@
-from torchvision import models
-import torch.nn as nn
-import matplotlib
-import numpy as np
-import torch
-import cv2
-import gc
-import io
-
-
-def _render_plot(values, figsize=(16, 16), dpi=16):
-    import matplotlib.pyplot as plt
-
-    fig = plt.figure(figsize=figsize)
-    plt.axes(ylim=(-1, 1))
-    plt.plot(values, color="black")
-    plt.gca().set_axis_off()
-    plt.subplots_adjust(top=1, bottom=0, right=1, left=0, hspace=0, wspace=0)
-    plt.margins(0, 0)
-
-    buf = io.BytesIO()
-    fig.savefig(buf, format="png", dpi=dpi)
-    buf.seek(0)
-    img_arr = np.frombuffer(buf.getvalue(), dtype=np.uint8)
-    buf.close()
-
-    img = cv2.imdecode(img_arr, 1)
-    if img is None:
-        raise RuntimeError("failed to decode plot image")
-
-    plt.clf()
-    plt.cla()
-    plt.close()
-    plt.close(fig)
-
-    return np.asarray(cv2.split(img), dtype=np.float32)
-
-
-def pre_func_ensemble(data=None, src="", ind_inference=0):
-    try:
-        import matplotlib.pyplot as plt
-
-        matplotlib.use("Agg")
-        plt.ioff()
-
-        real = np.asarray(data[0], dtype=np.float32)
-        imag = np.asarray(data[1], dtype=np.float32)
-        signal = real + 1j * imag
-
-        img_real = _render_plot(signal.real)
-        img_mag = _render_plot(np.abs(signal))
-
-        cv2.destroyAllWindows()
-        gc.collect()
-
-        print("Подготовка данных завершена")
-        print()
-        return [img_real, img_mag]
-
-    except Exception as exc:
-        print(str(exc))
-        return None
-
-
-def build_func_ensemble(file_model="", file_config="", num_classes=None):
-    try:
-        import matplotlib.pyplot as plt
-
-        matplotlib.use("Agg")
-        plt.ioff()
-        torch.cuda.empty_cache()
-
-        num_classes = 2
-        model1 = models.resnet18(pretrained=False)
-        model2 = models.resnet50(pretrained=False)
-
-        model1.fc = nn.Linear(model1.fc.in_features, num_classes)
-        model2.fc = nn.Linear(model2.fc.in_features, num_classes)
-
-        class Ensemble(nn.Module):
-            def __init__(self, model1, model2):
-                super().__init__()
-                self.model1 = model1
-                self.model2 = model2
-                self.fc = nn.Linear(2 * num_classes, num_classes)
-
-            def forward(self, x):
-                if isinstance(x, (list, tuple)):
-                    x1 = x[0]
-                    x2 = x[1] if len(x) > 1 else x[0]
-                else:
-                    x1 = x
-                    x2 = x
-                y1 = self.model1(x1)
-                y2 = self.model2(x2)
-                y = torch.cat((y1, y2), dim=1)
-                return self.fc(y)
-
-        model = Ensemble(model1, model2)
-
-        device = "cuda" if torch.cuda.is_available() else "cpu"
-        if device != "cpu":
-            model = model.to(device)
-        model.load_state_dict(torch.load(file_model, map_location=device))
-        model.eval()
-
-        cv2.destroyAllWindows()
-        gc.collect()
-
-        print("Инициализация модели завершена")
-        print()
-        return model
-
-    except Exception as exc:
-        print(str(exc))
-        return None
-
-
-def inference_func_ensemble(data=None, model=None, mapping=None, shablon=""):
-    try:
-        cv2.destroyAllWindows()
-        gc.collect()
-        torch.cuda.empty_cache()
-
-        device = "cuda" if torch.cuda.is_available() else "cpu"
-        if isinstance(data, (list, tuple)) and len(data) >= 2:
-            inputs = [
-                torch.unsqueeze(torch.tensor(data[0]).cpu(), 0).to(device).float(),
-                torch.unsqueeze(torch.tensor(data[1]).cpu(), 0).to(device).float(),
-            ]
-        else:
-            tensor = torch.unsqueeze(torch.tensor(data).cpu(), 0).to(device).float()
-            inputs = [tensor, tensor]
-
-        with torch.no_grad():
-            output = model(inputs)
-            _, predict = torch.max(output.data, 1)
-
-        prediction = mapping[int(np.asarray(predict.cpu())[0])]
-        print("PREDICTION" + shablon + ": " + prediction)
-
-        output = output.cpu()
-        label = np.asarray(np.argmax(output, axis=1))[0]
-        output = np.asarray(torch.squeeze(output, 0))
-        expon = np.exp(output - np.max(output))
-        probability = round((expon / expon.sum())[label], 2)
-
-        cv2.destroyAllWindows()
-        gc.collect()
-        print("Уверенность" + shablon + " в предсказании: " + str(probability))
-        print("Инференс завершен")
-        print()
-        return [prediction, probability]
-
-    except Exception as exc:
-        print(str(exc))
-        return None
-
-
-def post_func_ensemble(src="", model_type="", prediction="", model_id=0, ind_inference=0, data=None):
-    try:
-        import matplotlib.pyplot as plt
-
-        matplotlib.use("Agg")
-        plt.ioff()
-
-        if int(ind_inference) <= 100 and isinstance(data, (list, tuple)) and len(data) >= 2:
-            fig, ax = plt.subplots()
-            ax.imshow(np.moveaxis(data[0], 0, -1))
-            plt.savefig(src + "_inference_" + str(ind_inference) + "_" + prediction + "_real_" + str(model_id) + "_" + model_type + ".png")
-            plt.clf()
-            plt.cla()
-            plt.close(fig)
-            cv2.destroyAllWindows()
-            gc.collect()
-
-            fig, ax = plt.subplots()
-            ax.imshow(np.moveaxis(data[1], 0, -1))
-            plt.savefig(src + "_inference_" + str(ind_inference) + "_" + prediction + "_mod_" + str(model_id) + "_" + model_type + ".png")
-            plt.clf()
-            plt.cla()
-            plt.close(fig)
-            cv2.destroyAllWindows()
-            gc.collect()
-
-        plt.clf()
-        plt.cla()
-        plt.close()
-        cv2.destroyAllWindows()
-        gc.collect()
-
-        print("Постобработка завершена")
-        print()
-
-    except Exception as exc:
-        print(str(exc))
-        return None

NN_server/server.py

@@ -3,7 +3,6 @@ from dotenv import dotenv_values
 from common.runtime import load_root_env, validate_env, as_int, as_str
 import os
 import sys
-import re
 import matplotlib.pyplot as plt
 from Model import Model
 import numpy as np
@@ -16,6 +15,8 @@ import shutil
 import json
 import gc
 import logging
+import time
+import re
 
 TORCHSIG_PATH = "/app/torchsig"
 if TORCHSIG_PATH not in sys.path:
@@ -29,6 +30,7 @@ loop = asyncio.new_event_loop()
 asyncio.set_event_loop(loop)
 queue = asyncio.Queue()
 semaphore = asyncio.Semaphore(3)
+receive_data_lock = threading.Lock()
 
 prediction_list = []
 result_msg = {}
@@ -50,65 +52,96 @@ validate_env("NN_server/server.py", {
 })
 config = dict(dotenv_values(ROOT_ENV))
 
-
-def is_model_config_key(key, value):
-    return bool(re.fullmatch(r"NN_\d+", key or "")) and isinstance(value, str) and " && " in value
-
-
-def get_required_drone_streak(freq):
-    raw_value = config.get(f"DRONE_STREAK_{freq}", "1")
-    try:
-        return max(1, int(raw_value))
-    except (TypeError, ValueError):
-        logging.warning("Invalid DRONE_STREAK_%s=%r, falling back to 1", freq, raw_value)
-        return 1
-
-
-def update_drone_streak(freq, prediction):
-    if prediction == "drone":
-        drone_streaks[freq] = drone_streaks.get(freq, 0) + 1
-    else:
-        drone_streaks[freq] = 0
-
-    required = get_required_drone_streak(freq)
-    triggered = prediction == "drone" and drone_streaks[freq] >= required
-    logging.info(
-        "NN alarm gate freq=%s prediction=%s streak=%s/%s triggered=%s",
-        freq,
-        prediction,
-        drone_streaks[freq],
-        required,
-        triggered,
-    )
-    return 8 if triggered else 0
-
-
 if not config:
     raise RuntimeError("[NN_server/server.py] .env was loaded but no keys were parsed")
-if not any(is_model_config_key(key, value) for key, value in config.items()):
+MODEL_ENV_RE = re.compile(r"^NN_\d+$")
+
+if not any(MODEL_ENV_RE.match(key) for key in config):
     raise RuntimeError("[NN_server/server.py] no NN_* model entries configured")
 logging.info("NN config loaded from %s", ROOT_ENV)
 gen_server_ip = config['GENERAL_SERVER_IP']
 gen_server_port = config['GENERAL_SERVER_PORT']
-drone_streaks = {}
+INFERENCE_TELEMETRY_HOST = os.getenv('telemetry_host', '127.0.0.1')
+INFERENCE_TELEMETRY_PORT = os.getenv('telemetry_port', '5020')
+INFERENCE_TELEMETRY_ENDPOINT = os.getenv('telemetry_inference_endpoint', 'inference/result')
+INFERENCE_TELEMETRY_TIMEOUT_SEC = float(os.getenv('telemetry_inference_timeout_sec', '0.30'))
+INFERENCE_IMAGE_RE = re.compile(r"_inference_(\d+)_")
+
+
+def get_result_dir():
+    return config.get('SRC_RESULT', '')
+
+
+def collect_inference_images(result_id, model_name=''):
+    result_dir = get_result_dir()
+    if not result_dir or not os.path.isdir(result_dir):
+        return result_id, []
+
+    needle = f"_inference_{result_id}_"
+    model_suffix = f"_{model_name}.png" if model_name else ''
+    exact_images = []
+    grouped_images = {}
+
+    for name in sorted(os.listdir(result_dir)):
+        if not name.endswith('.png'):
+            continue
+        if model_suffix and not name.endswith(model_suffix):
+            continue
+        match = INFERENCE_IMAGE_RE.search(name)
+        if match is None:
+            continue
+
+        image_result_id = int(match.group(1))
+        grouped_images.setdefault(image_result_id, []).append(name)
+        if image_result_id == result_id and needle in name:
+            exact_images.append(name)
+
+    if exact_images:
+        return result_id, exact_images
+    return result_id, []
+
+
+def send_inference_result(payload):
+    try:
+        requests.post(
+            "http://{0}:{1}/{2}".format(
+                INFERENCE_TELEMETRY_HOST,
+                INFERENCE_TELEMETRY_PORT,
+                INFERENCE_TELEMETRY_ENDPOINT.lstrip('/'),
+            ),
+            json=payload,
+            timeout=INFERENCE_TELEMETRY_TIMEOUT_SEC,
+        )
+    except Exception as exc:
+        print(str(exc))
+
+
+def reset_directory_contents(path):
+    os.makedirs(path, exist_ok=True)
+    for name in os.listdir(path):
+        full_path = os.path.join(path, name)
+        try:
+            if os.path.isdir(full_path) and not os.path.islink(full_path):
+                shutil.rmtree(full_path)
+            else:
+                os.remove(full_path)
+        except FileNotFoundError:
+            continue
+
 
 def init_data_for_inference():
     try:
-        if os.path.isdir(config['SRC_RESULT']):
-            shutil.rmtree(config['SRC_RESULT'])
-        os.mkdir(config['SRC_RESULT'])
-        if os.path.isdir(config['SRC_EXAMPLE']):
-            shutil.rmtree(config['SRC_EXAMPLE'])
-        os.mkdir(config['SRC_EXAMPLE'])
+        reset_directory_contents(config['SRC_RESULT'])
+        reset_directory_contents(config['SRC_EXAMPLE'])
     except Exception as exc:
         print(str(exc))
         print()
 
     try:
         global model_list
-        for key, value in config.items():
-            if is_model_config_key(key, value):
-                params = value.split(' && ')
+        for key in config.keys():
+            if MODEL_ENV_RE.match(key):
+                params = config[key].split(' && ')
                 module = importlib.import_module('Models.' + params[4])
                 classes = {}
                 for value in params[9][1:-1].split(','):
@@ -144,11 +177,19 @@ def run_example():
 
 @app.route('/receive_data', methods=['POST'])
 def receive_data():
+    with receive_data_lock:
+        return _receive_data_locked()
+
+
+def _receive_data_locked():
     try:
         print()
-        data = json.loads(request.json)
+        data = request.json
+        if isinstance(data, str):
+            data = json.loads(data)
         print('#' * 100)
         print('Получен пакет ' + str(Model.get_ind_inference()))
+        result_id = Model.get_ind_inference()
         freq = int(data['freq'])
         print('Частота: ' + str(freq))
         # print('Канал: ' + str(data['channel']))
@@ -164,21 +205,49 @@ def receive_data():
                 print('-' * 100)
                 print(str(model))
                 result_msg[str(model.get_model_name())] = {'freq': freq}
-                prediction, probability = model.get_inference([np.asarray(data['data_real'], dtype=np.float32), np.asarray(data['data_imag'], dtype=np.float32)])
+                prediction, probability = model.get_inference([np.asarray(data['data_real'], dtype=np.float32), np.asarray(data['data_imag'], dtype=np.float32)], ind_inference=result_id)
                 result_msg[str(model.get_model_name())]['prediction'] = prediction
                 result_msg[str(model.get_model_name())]['probability'] = str(probability)
                 prediction_list.append(prediction)
+                image_result_id, images = collect_inference_images(result_id, model.get_model_name())
+                send_inference_result({
+                    'result_id': image_result_id,
+                    'ts': time.time(),
+                    'freq': str(freq),
+                    'model': model.get_model_name(),
+                    'prediction': prediction,
+                    'probability': float(probability),
+                    'drone_probability': float(probability) if prediction == 'drone' else 0.0,
+                    'drone_threshold': None,
+                    'images': images,
+                })
                 print('-' * 100)
                 print()
                 
                 try:
-                    result = update_drone_streak(freq, prediction_list[0])
-                    data_to_send={
-                        'freq': str(freq),
-                        'amplitude': result
-                        #'triggered': False if result < 7 else True,
-                        #'light_len': result
-                        }
+                                    
+                    result = 0
+                    freq_int = int(freq)
+                    prediction = prediction_list[0]
+                    prob = float(probability)
+
+                    if freq_int == 2400:
+                        if prediction in ["drone", "drone_noise"]:
+                            result += 0
+                        elif prediction == "wifi" and prob >= 0.95:
+                            result += 0
+
+                    elif freq_int == 1200:
+                        if prediction == "drone" and prob >= 0.95:
+                            result += 8
+
+                    elif freq_int == 915:
+                        result = 0
+
+                    data_to_send = {
+                        "freq": str(freq),
+                        "amplitude": result,
+                    }
                     response = requests.post("http://{0}:{1}/process_data".format(gen_server_ip, gen_server_port), json=data_to_send)
                     if response.status_code == 200:
                         print("Данные успешно отправлены!")

README.md

@@ -173,7 +173,8 @@ sudo systemctl stop dronedetector-sdr-5800.service
 sudo systemctl stop dronedetector-sdr-1200.service
 sudo systemctl stop dronedetector-sdr-2400.service
 sudo systemctl stop dronedetector-sdr-1500.service
-sudo systemctl stop dronedetector-sdr-915.service
+sudo systemctl stop dronedetector-sdr-868.service
+sudo systemctl stop dronedetector-sdr-868-915.service
 ```
 
 
@@ -197,6 +198,8 @@ since="$(systemctl show -p ActiveEnterTimestamp --value dronedetector-sdr-5800.s
 sudo journalctl -u dronedetector-sdr-5800.service --since "$since" --no-pager
 ```
 
+
+
 ### Просмотр логов от server-to-master   
 ``` bash
 docker compose -f deploy/docker/docker-compose.yml logs --timestamps dronedetector-server-to-master | tail -n 50
@@ -207,24 +210,13 @@ docker compose -f deploy/docker/docker-compose.yml logs --timestamps dronedetect
 sudo hackrf_spiflash -w hackrf_one_usb.bin
 ```
 
-### Wide_read_energy
-``` bash
-./.venv-sdr/bin/python read_energy_wide.py \
-    --serial 0000000000000000a18c63dc2a83b813 \
-    --sample-rate 20000000 \
-    --base 6000 \
-    --roof 5700 \
-    --step 20
-```
-
-### Проверка тревоги 
-``` bash
-curl -X POST 'http://127.0.0.1:5010/process_data' \
-    -H 'Content-Type: application/json' \
-    -d '{"freq":"1200","amplitude":9}'
-```
+./.venv-sdr/bin/python scripts_nn/data_saver_headless.py   --serial 000  --freq 4500000000   --save-dir /home/sibscience-4/Dataset/3300   --file-tag DJI_3_   --samp-rate 20000000   --split-size 400000   --delay 0.1   --rf-gain 12   --if-gain 30   --bb-gain 36
 
-### Read_energy
-``` bash 
-.venv-sdr/bin/python read_energy.py 
+### Парсинг логов 
+```  bash
+.venv-train/bin/python scripts/capture_nn_results.py \
+    --output logs/nn_results_live_6gb.csv \
+    --format csv \
+    --max-bytes 6442450944 \
+    --tail 0
 ```

capture_hourly.sh

@@ -3,105 +3,123 @@ set -Eeuo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 SCRIPT_OWNER="${CAPTURE_USER:-$(stat -c %U "$SCRIPT_DIR")}"
-SCRIPT_OWNER_HOME="$(getent passwd "$SCRIPT_OWNER" | cut -d: -f6)"
+SCRIPT_OWNER_HOME="$(getent passwd "$SCRIPT_OWNER" | cut -d: -f6 || true)"
 cd "$SCRIPT_DIR"
 
-source "$SCRIPT_DIR/.env"
 ############################
 # НАСТРОЙКИ
 ############################
 
-BASE_DIR="${CAPTURE_BASE_DIR:-${SCRIPT_OWNER_HOME}/dataset/noise}"
+BASE_DIR="/mnt/data/dataset_6_5_26"
 
-# Путь к python из venv
 PYTHON_BIN="${PYTHON_BIN:-$SCRIPT_DIR/.venv-sdr/bin/python}"
-
-# Путь к headless скрипту
 SCRIPT_PATH="${SCRIPT_PATH:-$SCRIPT_DIR/scripts_nn/data_saver_headless.py}"
+ENV_FILE="${ENV_FILE:-$SCRIPT_DIR/.env}"
 
 RUN_ONCE="${RUN_ONCE:-0}"
 CAPTURE_LOG_FILE="${CAPTURE_LOG_FILE:-$BASE_DIR/capture_hourly.log}"
 
 SYSTEMCTL_BIN=(systemctl)
+
 CURRENT_CAPTURE_PID=""
+CURRENT_MOCK_PID=""
 CURRENT_SERVICE_UNIT=""
-
-
+STOPPED_SERVICE_UNIT=""
 
 # Лимиты
+PER_FREQ_LIMIT_GIB="${PER_FREQ_LIMIT_GIB:-12}"
+TOTAL_LIMIT_GIB="${TOTAL_LIMIT_GIB:-266}"
 
-lim_all=10
-PER_FREQ_LIMIT_BYTES=$((1 * 1024 * 1024 * 1024))     #  GiB на частоту за запуск
-TOTAL_LIMIT_BYTES=$((lim_all * 1024 * 1024 * 1024))      # общий лимит  GiB
-CYCLE_SECONDS=1                               # один цикл в час
+PER_FREQ_LIMIT_BYTES=$((PER_FREQ_LIMIT_GIB * 1024 * 1024 * 1024))
+TOTAL_LIMIT_BYTES=$((TOTAL_LIMIT_GIB * 1024 * 1024 * 1024))
+
+# Для обычного hourly можно поставить 3600.
+# Для RUN_ONCE это почти не важно.
+CYCLE_SECONDS="${CYCLE_SECONDS:-1}"
 
 # Параметры SDR
-SAMP_RATE="20e6"
-SPLIT_SIZE="400000"
-DELAY="0.01"
-RF_GAIN="12"
-IF_GAIN="30"
-BB_GAIN="36"
+SAMP_RATE="${SAMP_RATE:-20e6}"
+SPLIT_SIZE="${SPLIT_SIZE:-400000}"
+DELAY="${DELAY:-0.25}"
+RF_GAIN="${RF_GAIN:-12}"
+IF_GAIN="${IF_GAIN:-12}"
+BB_GAIN="${BB_GAIN:-0}"
 
 ############################
-# ЧАСТОТЫ И SERIAL ИЗ ENV
+# MOCK SENDER
 ############################
 
-ORDER=(433)
+CAPTURE_MOCK_SEND_ENABLED="${CAPTURE_MOCK_SEND_ENABLED:-1}"
+CAPTURE_MOCK_HOST="${CAPTURE_MOCK_HOST:-127.0.0.1}"
+CAPTURE_MOCK_INTERVAL_SECONDS="${CAPTURE_MOCK_INTERVAL_SECONDS:-1}"
+CAPTURE_MOCK_TIMEOUT_SECONDS="${CAPTURE_MOCK_TIMEOUT_SECONDS:-0.3}"
+CAPTURE_MOCK_LOG_SUCCESS="${CAPTURE_MOCK_LOG_SUCCESS:-0}"
 
+############################
+# ВСПОМОГАТЕЛЬНОЕ
+############################
 
-declare -A SERIAL
-declare -A FREQ_HZ
-declare -A SERVICE_UNIT
+log() {
+  printf '[%s] %s\n' "$(date '+%F %T')" "$*"
+}
 
-SERIAL[433]="$hack_433"
-FREQ_HZ[433]="433000000"
+systemctl_run() {
+  "${SYSTEMCTL_BIN[@]}" "$@"
+}
 
-SERIAL[750]="$hack_750"
-FREQ_HZ[750]="750000000"
+env_get() {
+  local key="$1"
+  local default="${2:-}"
 
+  if [[ ! -f "$ENV_FILE" ]]; then
+    printf '%s\n' "$default"
+    return 0
+  fi
 
-SERIAL[915]="$hack_915"
-FREQ_HZ[915]="915000000"
+  awk -v key="$key" -v default="$default" '
+    BEGIN { found = 0 }
 
-SERIAL[1200]="$hack_1200"
-FREQ_HZ[1200]="1200000000"
+    $0 ~ "^[[:space:]]*" key "=" {
+      value = $0
 
-SERIAL[2400]="$hack_2400"
-FREQ_HZ[2400]="2400000000"
+      sub("^[[:space:]]*" key "=", "", value)
+      sub("[[:space:]]+#.*$", "", value)
+      gsub("^[[:space:]]+|[[:space:]]+$", "", value)
 
-SERIAL[3300]="$hack_3300"
-FREQ_HZ[3300]="3300000000"
+      if ((substr(value, 1, 1) == "\"" && substr(value, length(value), 1) == "\"") ||
+          (substr(value, 1, 1) == "'"'"'" && substr(value, length(value), 1) == "'"'"'")) {
+        value = substr(value, 2, length(value) - 2)
+      }
 
-SERIAL[4500]="$hack_4500"
-FREQ_HZ[4500]="4500000000"
+      print value
+      found = 1
+      exit
+    }
 
-SERIAL[5200]="$hack_5200"
-FREQ_HZ[5200]="5200000000"
+    END {
+      if (!found) {
+        print default
+      }
+    }
+  ' "$ENV_FILE"
+}
 
-SERIAL[5800]="$hack_5800"
-FREQ_HZ[5800]="5800000000"
+mock_bool_enabled() {
+  case "${1,,}" in
+    1|true|yes|on) return 0 ;;
+    *) return 1 ;;
+  esac
+}
 
-SERVICE_UNIT[433]="dronedetector-sdr-433.service"
-SERVICE_UNIT[750]="dronedetector-sdr-750.service"
-SERVICE_UNIT[915]="dronedetector-sdr-915.service"
-SERVICE_UNIT[1200]="dronedetector-sdr-1200.service"
-SERVICE_UNIT[2400]="dronedetector-sdr-2400.service"
-SERVICE_UNIT[3300]="dronedetector-sdr-3300.service"
-SERVICE_UNIT[4500]="dronedetector-sdr-4500.service"
-SERVICE_UNIT[5200]="dronedetector-sdr-5200.service"
-SERVICE_UNIT[5800]="dronedetector-sdr-5800.service"
+mock_url() {
+  local port endpoint
 
-############################
-# ВСПОМОГАТЕЛЬНОЕ
-############################
+  port="${CAPTURE_MOCK_PORT:-$(env_get locport "$(env_get GENERAL_SERVER_PORT 5010)")}"
+  endpoint="${CAPTURE_MOCK_ENDPOINT:-$(env_get freq_endpoint process_data)}"
 
-log() {
-  printf '[%s] %s\n' "$(date '+%F %T')" "$*"
-}
+  endpoint="${endpoint#/}"
 
-systemctl_run() {
-  "${SYSTEMCTL_BIN[@]}" "$@"
+  printf 'http://%s:%s/%s' "$CAPTURE_MOCK_HOST" "$port" "$endpoint"
 }
 
 service_exists() {
@@ -109,10 +127,60 @@ service_exists() {
   systemctl_run show "$unit" >/dev/null 2>&1
 }
 
+service_is_active() {
+  local unit="$1"
+  systemctl_run is-active --quiet "$unit" >/dev/null 2>&1
+}
+
+dir_size_bytes() {
+  local path="$1"
+
+  if [[ -e "$path" ]]; then
+    du -sb "$path" 2>/dev/null | awk '{print $1}'
+  else
+    echo 0
+  fi
+}
+
+total_size_bytes() {
+  dir_size_bytes "$BASE_DIR"
+}
+
+terminate_pid() {
+  local pid="${1:-}"
+
+  if [[ -z "$pid" ]]; then
+    return 0
+  fi
+
+  if ! kill -0 "$pid" 2>/dev/null; then
+    return 0
+  fi
+
+  kill -TERM "$pid" 2>/dev/null || true
+
+  for _ in {1..10}; do
+    if ! kill -0 "$pid" 2>/dev/null; then
+      break
+    fi
+    sleep 1
+  done
+
+  if kill -0 "$pid" 2>/dev/null; then
+    log "PID=$pid не завершился по TERM, отправляю KILL"
+    kill -KILL "$pid" 2>/dev/null || true
+  fi
+
+  wait "$pid" 2>/dev/null || true
+}
+
 stop_band_service() {
   local band="$1"
   local unit="${SERVICE_UNIT[$band]:-}"
 
+  STOPPED_SERVICE_UNIT=""
+  CURRENT_SERVICE_UNIT=""
+
   if [[ -z "$unit" ]]; then
     log "Для band=$band не найден service unit"
     return 0
@@ -124,33 +192,137 @@ stop_band_service() {
   fi
 
   log "Останавливаю service $unit перед записью band=$band"
-  systemctl_run stop "$unit"
+
+  if systemctl_run stop "$unit"; then
+    log "Service $unit остановлен или уже был остановлен"
+  else
+    log "Не удалось остановить service $unit"
+  fi
+
+  STOPPED_SERVICE_UNIT="$unit"
   CURRENT_SERVICE_UNIT="$unit"
+
+  return 0
 }
 
-start_current_service() {
-  if [[ -z "$CURRENT_SERVICE_UNIT" ]]; then
+start_stopped_service() {
+  local unit="${STOPPED_SERVICE_UNIT:-}"
+
+  if [[ -z "$unit" ]]; then
     return 0
   fi
 
-  log "Запускаю service $CURRENT_SERVICE_UNIT после записи"
-  systemctl_run start "$CURRENT_SERVICE_UNIT"
+  log "Запускаю service $unit после записи"
+
+  if systemctl_run start "$unit"; then
+    log "Service $unit запущен"
+  else
+    log "Не удалось запустить service $unit"
+    systemctl_run status "$unit" --no-pager || true
+  fi
+
+  STOPPED_SERVICE_UNIT=""
   CURRENT_SERVICE_UNIT=""
 }
 
+start_mock_sender() {
+  local band="$1"
+  local log_file="$2"
+  local url
+
+  CURRENT_MOCK_PID=""
+
+  if ! mock_bool_enabled "$CAPTURE_MOCK_SEND_ENABLED"; then
+    log "Mock sender отключен CAPTURE_MOCK_SEND_ENABLED=$CAPTURE_MOCK_SEND_ENABLED"
+    return 0
+  fi
+
+  url="$(mock_url)"
+
+  log "Старт mock sender band=$band url=$url amplitude=0 interval=${CAPTURE_MOCK_INTERVAL_SECONDS}s"
+
+  "$PYTHON_BIN" - \
+    "$url" \
+    "$band" \
+    "$CAPTURE_MOCK_INTERVAL_SECONDS" \
+    "$CAPTURE_MOCK_TIMEOUT_SECONDS" \
+    "$CAPTURE_MOCK_LOG_SUCCESS" \
+    >>"$log_file" 2>&1 <<'PY' &
+
+import json
+import sys
+import time
+import urllib.request
+
+
+url = sys.argv[1]
+freq = str(sys.argv[2])
+interval = float(sys.argv[3])
+timeout = float(sys.argv[4])
+log_success = sys.argv[5].lower() in {"1", "true", "yes", "on"}
+
+payload = json.dumps({"freq": freq, "amplitude": 0}).encode("utf-8")
+headers = {"Content-Type": "application/json"}
+
+print(
+    f"[capture-mock] started url={url} freq={freq} amplitude=0 interval={interval}",
+    flush=True,
+)
+
+while True:
+    try:
+        req = urllib.request.Request(
+            url,
+            data=payload,
+            headers=headers,
+            method="POST",
+        )
+
+        with urllib.request.urlopen(req, timeout=timeout) as response:
+            if log_success:
+                print(f"[capture-mock] sent status={response.status}", flush=True)
+
+    except Exception as exc:
+        print(f"[capture-mock] send failed: {exc}", flush=True)
+
+    time.sleep(interval)
+PY
+
+  CURRENT_MOCK_PID=$!
+  log "Mock sender PID=$CURRENT_MOCK_PID"
+}
+
+stop_mock_sender() {
+  local pid="${1:-}"
+
+  if [[ -z "$pid" ]]; then
+    return 0
+  fi
+
+  if kill -0 "$pid" 2>/dev/null; then
+    log "Останавливаю mock sender PID=$pid"
+    terminate_pid "$pid"
+  fi
+}
+
 cleanup_capture() {
-  if [[ -n "$CURRENT_CAPTURE_PID" ]] && kill -0 "$CURRENT_CAPTURE_PID" 2>/dev/null; then
-    log "Останавливаю текущий PID=$CURRENT_CAPTURE_PID при завершении скрипта"
-    kill -TERM "$CURRENT_CAPTURE_PID" 2>/dev/null || true
-    wait "$CURRENT_CAPTURE_PID" 2>/dev/null || true
+  local rc=$?
+
+  if [[ -n "${CURRENT_CAPTURE_PID:-}" ]] && kill -0 "$CURRENT_CAPTURE_PID" 2>/dev/null; then
+    log "Останавливаю текущий capture PID=$CURRENT_CAPTURE_PID"
+    terminate_pid "$CURRENT_CAPTURE_PID"
   fi
   CURRENT_CAPTURE_PID=""
 
-  if [[ -n "$CURRENT_SERVICE_UNIT" ]]; then
-    log "Восстанавливаю service $CURRENT_SERVICE_UNIT при завершении скрипта"
-    systemctl_run start "$CURRENT_SERVICE_UNIT" || true
-    CURRENT_SERVICE_UNIT=""
+  if [[ -n "${CURRENT_MOCK_PID:-}" ]] && kill -0 "$CURRENT_MOCK_PID" 2>/dev/null; then
+    log "Останавливаю текущий mock sender PID=$CURRENT_MOCK_PID"
+    terminate_pid "$CURRENT_MOCK_PID"
   fi
+  CURRENT_MOCK_PID=""
+
+  start_stopped_service
+
+  exit "$rc"
 }
 
 on_signal() {
@@ -159,18 +331,60 @@ on_signal() {
   exit 130
 }
 
-dir_size_bytes() {
-  local path="$1"
-  if [[ -e "$path" ]]; then
-    du -sb "$path" 2>/dev/null | awk '{print $1}'
-  else
-    echo 0
-  fi
-}
+############################
+# ЧАСТОТЫ И SERIAL
+############################
 
-total_size_bytes() {
-  dir_size_bytes "$BASE_DIR"
-}
+ORDER=(2400)
+
+declare -A SERIAL
+declare -A FREQ_HZ
+declare -A SERVICE_UNIT
+
+SERIAL[433]="$(env_get hack_433)"
+FREQ_HZ[433]="433000000"
+
+SERIAL[750]="$(env_get hack_750)"
+FREQ_HZ[750]="750000000"
+
+SERIAL[868]="$(env_get hack_868)"
+FREQ_HZ[868]="868000000"
+
+SERIAL[915]="$(env_get hack_915)"
+FREQ_HZ[915]="915000000"
+
+SERIAL[1200]="$(env_get hack_1200)"
+FREQ_HZ[1200]="1200000000"
+
+SERIAL[2400]="$(env_get hack_2400)"
+FREQ_HZ[2400]="2400000000"
+
+SERIAL[3300]="$(env_get hack_3300)"
+FREQ_HZ[3300]="3300000000"
+
+SERIAL[4500]="$(env_get hack_4500)"
+FREQ_HZ[4500]="4500000000"
+
+SERIAL[5200]="$(env_get hack_5200)"
+FREQ_HZ[5200]="5200000000"
+
+SERIAL[5800]="$(env_get hack_5800)"
+FREQ_HZ[5800]="5800000000"
+
+SERVICE_UNIT[433]="dronedetector-sdr-433.service"
+SERVICE_UNIT[750]="dronedetector-sdr-750.service"
+SERVICE_UNIT[868]="dronedetector-sdr-868.service"
+SERVICE_UNIT[915]="dronedetector-sdr-915.service"
+SERVICE_UNIT[1200]="dronedetector-sdr-1200.service"
+SERVICE_UNIT[2400]="dronedetector-sdr-2400.service"
+SERVICE_UNIT[3300]="dronedetector-sdr-3300.service"
+SERVICE_UNIT[4500]="dronedetector-sdr-4500.service"
+SERVICE_UNIT[5200]="dronedetector-sdr-5200.service"
+SERVICE_UNIT[5800]="dronedetector-sdr-5800.service"
+
+############################
+# ОСНОВНАЯ ЛОГИКА
+############################
 
 ensure_requirements() {
   if [[ ! -x "$PYTHON_BIN" ]]; then
@@ -203,6 +417,7 @@ ensure_requirements() {
   if [[ -n "${CAPTURE_ORDER:-}" ]]; then
     ORDER=()
     local band
+
     for band in ${CAPTURE_ORDER//,/ }; do
       ORDER+=("$band")
     done
@@ -217,25 +432,36 @@ ensure_requirements() {
   log "BASE_DIR: $BASE_DIR"
   log "ORDER: ${ORDER[*]}"
   log "RUN_ONCE: $RUN_ONCE"
-
+  log "PER_FREQ_LIMIT_GIB: $PER_FREQ_LIMIT_GIB"
+  log "TOTAL_LIMIT_GIB: $TOTAL_LIMIT_GIB"
+  log "CYCLE_SECONDS: $CYCLE_SECONDS"
+  log "CAPTURE_MOCK_SEND_ENABLED: $CAPTURE_MOCK_SEND_ENABLED"
+  log "PYTHON_BIN: $PYTHON_BIN"
+  log "SCRIPT_PATH: $SCRIPT_PATH"
 }
 
 run_one_freq() {
   local band="$1"
-  local serial="${SERIAL[$band]}"
-  local freq="${FREQ_HZ[$band]}"
+  local serial="${SERIAL[$band]:-}"
+  local freq="${FREQ_HZ[$band]:-}"
 
   if [[ -z "$serial" ]]; then
     log "Для band=$band пустой serial, пропускаю"
     return 0
   fi
 
+  if [[ -z "$freq" ]]; then
+    log "Для band=$band не задана частота, пропускаю"
+    return 0
+  fi
+
   local ts out_dir log_file
   ts="$(date '+%F_%H-%M-%S')"
   out_dir="$BASE_DIR/$band/$ts"
   log_file="$out_dir/run.log"
 
   log "Старт band=$band serial=$serial freq=$freq dir=$out_dir"
+
   if ! mkdir -p "$out_dir"; then
     log "Не удалось создать каталог $out_dir"
     return 1
@@ -258,64 +484,71 @@ run_one_freq() {
 
   local pid=$!
   CURRENT_CAPTURE_PID="$pid"
-  log "PID=$pid"
+  log "Capture PID=$pid"
+
+  start_mock_sender "$band" "$log_file"
+  local mock_pid="$CURRENT_MOCK_PID"
 
   while kill -0 "$pid" 2>/dev/null; do
     local cur_dir_size cur_total_size
+
     cur_dir_size="$(dir_size_bytes "$out_dir")"
     cur_total_size="$(total_size_bytes)"
 
     if (( cur_total_size >= TOTAL_LIMIT_BYTES )); then
-      log "Достигнут общий лимит $lim_all GiB. Останавливаю PID=$pid"
-      kill -TERM "$pid" 2>/dev/null || true
-      wait "$pid" 2>/dev/null || true
+      log "Достигнут общий лимит ${TOTAL_LIMIT_GIB} GiB. Останавливаю PID=$pid"
+
+      terminate_pid "$pid"
       CURRENT_CAPTURE_PID=""
-      start_current_service
+
+      stop_mock_sender "$mock_pid"
+      CURRENT_MOCK_PID=""
+
+      start_stopped_service
+
       return 2
     fi
 
     if (( cur_dir_size >= PER_FREQ_LIMIT_BYTES )); then
-      log "Для band=$band достигнут лимит 3 GiB. Останавливаю PID=$pid"
-      kill -TERM "$pid" 2>/dev/null || true
+      log "Для band=$band достигнут лимит ${PER_FREQ_LIMIT_GIB} GiB. Останавливаю PID=$pid"
 
-      for _ in {1..10}; do
-        if ! kill -0 "$pid" 2>/dev/null; then
-          break
-        fi
-        sleep 1
-      done
-
-      if kill -0 "$pid" 2>/dev/null; then
-        log "PID=$pid не завершился по TERM, отправляю KILL"
-        kill -KILL "$pid" 2>/dev/null || true
-      fi
+      terminate_pid "$pid"
+      CURRENT_CAPTURE_PID=""
 
-      wait "$pid" 2>/dev/null || true
       break
     fi
 
     sleep 1
   done
 
+  wait "$pid" 2>/dev/null || true
   CURRENT_CAPTURE_PID=""
-  start_current_service
+
+  stop_mock_sender "$mock_pid"
+  CURRENT_MOCK_PID=""
+
+  start_stopped_service
+
   log "Завершен band=$band, размер=$(du -sh "$out_dir" | awk '{print $1}')"
+
   return 0
 }
 
 main_loop() {
   while true; do
     local total_before cycle_start elapsed sleep_left
+
     total_before="$(total_size_bytes)"
 
     if (( total_before >= TOTAL_LIMIT_BYTES )); then
-      log "Общий размер уже >=  GiB, выхожу"
+      log "Общий размер уже >= ${TOTAL_LIMIT_GIB} GiB, выхожу"
       break
     fi
 
     cycle_start="$(date +%s)"
     log "Новый цикл"
 
+    local band
     for band in "${ORDER[@]}"; do
       if (( $(total_size_bytes) >= TOTAL_LIMIT_BYTES )); then
         log "Общий лимит достигнут внутри цикла, выхожу"
@@ -323,14 +556,15 @@ main_loop() {
       fi
 
       run_one_freq "$band" || {
-        rc=$?
-        if [[ $rc -eq 2 ]]; then
+        local rc=$?
+
+        if [[ "$rc" -eq 2 ]]; then
           log "Остановка по общему лимиту"
           return 0
-        else
-          log "Ошибка записи band=$band rc=$rc"
-          return "$rc"
         fi
+
+        log "Ошибка записи band=$band rc=$rc"
+        return "$rc"
       }
     done
 
@@ -343,7 +577,7 @@ main_loop() {
     sleep_left=$(( CYCLE_SECONDS - elapsed ))
 
     if (( sleep_left > 0 )); then
-      log "Цикл занял ${elapsed} сек, жду ${sleep_left} сек до следующего часа"
+      log "Цикл занял ${elapsed} сек, жду ${sleep_left} сек"
       sleep "$sleep_left"
     else
       log "Цикл занял ${elapsed} сек, паузы нет"

deploy/docker/docker-compose.yml

@@ -11,18 +11,7 @@ services:
       - PYTHONPATH=/app
       - JAMMER_STATE_FILE=/app/runtime/jammer_active.flag
     working_dir: /app
-    command:
-      - uvicorn
-      - src.server_to_master:app
-      - --host
-      - 0.0.0.0
-      - --port
-      - "5010"
-      - --reload
-      - --reload-dir
-      - /app/src
-      - --reload-dir
-      - /app/common
+    command: ["python3", "-m", "src.server_to_master"]
     restart: unless-stopped
     ports:
       - "5010:5010"
@@ -31,6 +20,7 @@ services:
       - ../../runtime:/app/runtime
       - ../../src:/app/src
       - ../../common:/app/common
+      - ../../train_scripts:/app/train_scripts:ro
     networks:
       - dronedetector-net
     extra_hosts:
@@ -47,6 +37,7 @@ services:
     environment:
       - PYTHONPATH=/app:/app/NN_server
       - NN_HOT_RELOAD=${NN_HOT_RELOAD:-1}
+      - telemetry_host=dronedetector-telemetry-server
     working_dir: /app/NN_server
     command:
       - sh
@@ -78,18 +69,7 @@ services:
     environment:
       - PYTHONPATH=/app
     working_dir: /app
-    command:
-      - uvicorn
-      - telemetry.telemetry_server:app
-      - --host
-      - 0.0.0.0
-      - --port
-      - "5020"
-      - --reload
-      - --reload-dir
-      - /app/telemetry
-      - --reload-dir
-      - /app/common
+    command: ["python3", "-m", "telemetry.telemetry_server"]
     restart: unless-stopped
     ports:
       - "5020:5020"
@@ -97,6 +77,7 @@ services:
       - ../../.env:/app/.env:ro
       - ../../telemetry:/app/telemetry
       - ../../common:/app/common
+      - ../../NN_server/result:/app/inference_result:ro
     networks:
       - dronedetector-net
 

deploy/systemd/dronedetector-compose.service

@@ -8,9 +8,9 @@ Requires=docker.service
 Type=oneshot
 WorkingDirectory=__PROJECT_ROOT__
 RemainAfterExit=yes
-ExecStart=/usr/bin/docker compose -f __PROJECT_ROOT__/deploy/docker/docker-compose.yml up -d
+ExecStart=/usr/bin/docker compose -f __PROJECT_ROOT__/deploy/docker/docker-compose.yml up -d --build
 ExecStop=/usr/bin/docker compose -f __PROJECT_ROOT__/deploy/docker/docker-compose.yml down
-ExecReload=/usr/bin/docker compose -f __PROJECT_ROOT__/deploy/docker/docker-compose.yml up -d
+ExecReload=/usr/bin/docker compose -f __PROJECT_ROOT__/deploy/docker/docker-compose.yml up -d --build
 TimeoutStartSec=0
 
 [Install]

deploy/systemd/dronedetector-sdr-1200.service

@@ -10,7 +10,8 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
-ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_1200.py
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
+ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python orange_scripts/main_1200.py
 Restart=always
 RestartSec=3
 

deploy/systemd/dronedetector-sdr-1500.service

@@ -10,6 +10,7 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
 ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_1500.py
 Restart=always
 RestartSec=3

deploy/systemd/dronedetector-sdr-2400.service

@@ -10,7 +10,8 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
-ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_2400.py
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
+ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python orange_scripts/main_2400.py
 Restart=always
 RestartSec=3
 

deploy/systemd/dronedetector-sdr-3300.service

@@ -10,6 +10,7 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
 ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_3300.py
 Restart=always
 RestartSec=3

deploy/systemd/dronedetector-sdr-433.service

@@ -10,6 +10,7 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
 ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_433.py
 Restart=always
 RestartSec=3

deploy/systemd/dronedetector-sdr-4500.service

@@ -10,6 +10,7 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
 ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_4500.py
 Restart=always
 RestartSec=3

deploy/systemd/dronedetector-sdr-5200.service

@@ -10,6 +10,7 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
 ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_5200.py
 Restart=always
 RestartSec=3

deploy/systemd/dronedetector-sdr-5800.service

@@ -10,6 +10,7 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
 ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_5800.py
 Restart=always
 RestartSec=3

deploy/systemd/dronedetector-sdr-750.service

@@ -10,6 +10,7 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
 ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_750.py
 Restart=always
 RestartSec=3

deploy/systemd/dronedetector-sdr-868-915.service

@@ -0,0 +1,19 @@
+[Unit]
+Description=DroneDetector SDR Router 868/915 Shared HackRF
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+User=__RUN_USER__
+Group=__RUN_GROUP__
+WorkingDirectory=__PROJECT_ROOT__
+EnvironmentFile=__PROJECT_ROOT__/.env
+Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
+ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_868_915_router.py
+Restart=always
+RestartSec=3
+
+[Install]
+WantedBy=multi-user.target

deploy/systemd/dronedetector-sdr-868.service

@@ -0,0 +1,20 @@
+[Unit]
+Description=DroneDetector SDR Scanner 868 MHz
+After=network-online.target dronedetector-sdr-868-915.service
+Wants=network-online.target
+Requires=dronedetector-sdr-868-915.service
+
+[Service]
+Type=simple
+User=__RUN_USER__
+Group=__RUN_GROUP__
+WorkingDirectory=__PROJECT_ROOT__
+EnvironmentFile=__PROJECT_ROOT__/.env
+Environment=PYTHONPATH=__PROJECT_ROOT__
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
+ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_868.py
+Restart=always
+RestartSec=3
+
+[Install]
+WantedBy=multi-user.target

deploy/systemd/dronedetector-sdr-915.service

@@ -1,7 +1,8 @@
 [Unit]
 Description=DroneDetector SDR Scanner 915 MHz
-After=network-online.target
+After=network-online.target dronedetector-sdr-868-915.service
 Wants=network-online.target
+Requires=dronedetector-sdr-868-915.service
 
 [Service]
 Type=simple
@@ -10,7 +11,8 @@ Group=__RUN_GROUP__
 WorkingDirectory=__PROJECT_ROOT__
 EnvironmentFile=__PROJECT_ROOT__/.env
 Environment=PYTHONPATH=__PROJECT_ROOT__
-ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python src/main_915.py
+ExecStartPre=/usr/local/bin/dronedetector-precheck-sdr.sh
+ExecStart=__PROJECT_ROOT__/.venv-sdr/bin/python orange_scripts/main_915.py
 Restart=always
 RestartSec=3
 

deploy/systemd/precheck-sdr.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if ! command -v hackrf_info >/dev/null 2>&1; then
+  echo "[dronedetector-precheck] hackrf_info not found. Install hackrf-tools/hackrf package." >&2
+  exit 1
+fi
+
+if ! command -v gnuradio-config-info >/dev/null 2>&1; then
+  echo "[dronedetector-precheck] gnuradio-config-info not found. Install gnuradio." >&2
+  exit 1
+fi
+
+if ! python3 -c "import osmosdr" >/dev/null 2>&1; then
+  echo "[dronedetector-precheck] Python module osmosdr not importable." >&2
+  exit 1
+fi
+
+if ! hackrf_info 2>/dev/null | grep -q "Found HackRF"; then
+  echo "[dronedetector-precheck] HackRF device was not detected by hackrf_info." >&2
+  exit 1
+fi

install_all.sh

@@ -7,13 +7,11 @@ SYSTEMD_TARGET_DIR="/etc/systemd/system"
 RUN_USER="${SUDO_USER:-${USER}}"
 RUN_GROUP="$(id -gn "${RUN_USER}")"
 
-SOURCE_ARCHIVES=(
-  "torchsig.tar.gz:torchsig:pyproject.toml"
-)
-
 SDR_UNITS=(
   dronedetector-sdr-433.service
   dronedetector-sdr-750.service
+  dronedetector-sdr-868-915.service
+  dronedetector-sdr-868.service
   dronedetector-sdr-1500.service
   dronedetector-sdr-3300.service
   dronedetector-sdr-4500.service
@@ -24,8 +22,6 @@ SDR_UNITS=(
   dronedetector-sdr-2400.service
 )
 
-CONFIGURED_SDR_UNITS=()
-
 log() {
   printf '[install_all] %s\n' "$*"
 }
@@ -35,51 +31,6 @@ die() {
   exit 1
 }
 
-sdr_unit_env_key() {
-  local unit="$1"
-  local band="${unit#dronedetector-sdr-}"
-  band="${band%.service}"
-  printf 'hack_%s\n' "$band"
-}
-
-get_env_value() {
-  local key="$1"
-  awk -F= -v key="$key" '
-    $1 == key {
-      value = substr($0, index($0, "=") + 1)
-      sub(/^[[:space:]]+/, "", value)
-      sub(/[[:space:]]+$/, "", value)
-      gsub(/^"/, "", value)
-      gsub(/"$/, "", value)
-      gsub(/^'\''/, "", value)
-      gsub(/'\''$/, "", value)
-      print value
-      exit
-    }
-  ' "${PROJECT_ROOT}/.env"
-}
-
-populate_configured_sdr_units() {
-  CONFIGURED_SDR_UNITS=()
-
-  local unit env_key env_value
-  for unit in "${SDR_UNITS[@]}"; do
-    env_key="$(sdr_unit_env_key "$unit")"
-    env_value="$(get_env_value "$env_key")"
-    if [[ -n "$env_value" ]]; then
-      CONFIGURED_SDR_UNITS+=("$unit")
-    else
-      log "Skipping ${unit}: ${env_key} is empty in .env"
-    fi
-  done
-
-  if [[ "${#CONFIGURED_SDR_UNITS[@]}" -eq 0 ]]; then
-    log "No SDR units are configured in .env"
-  else
-    log "Configured SDR units: ${CONFIGURED_SDR_UNITS[*]}"
-  fi
-}
-
 print_failure_logs() {
   log "Collecting diagnostics..."
   systemctl --no-pager --full status dronedetector-compose.service || true
@@ -108,35 +59,6 @@ require_root() {
   fi
 }
 
-extract_local_source_archives() {
-  local spec archive_rel target_rel sentinel_rel
-  local archive_path target_path sentinel_path
-
-  for spec in "${SOURCE_ARCHIVES[@]}"; do
-    IFS=':' read -r archive_rel target_rel sentinel_rel <<< "$spec"
-    archive_path="${PROJECT_ROOT}/${archive_rel}"
-    target_path="${PROJECT_ROOT}/${target_rel}"
-    sentinel_path="${target_path}/${sentinel_rel}"
-
-    if [[ -f "${sentinel_path}" ]]; then
-      log "Vendored source already available: ${target_rel}"
-      continue
-    fi
-
-    if [[ -e "${target_path}" ]]; then
-      die "Found ${target_path}, but ${sentinel_rel} is missing. Remove or repair this directory, then rerun the installer."
-    fi
-
-    [[ -f "${archive_path}" ]] || die "Missing vendored source ${target_path} and archive ${archive_path}"
-    command -v tar >/dev/null 2>&1 || die "tar is required to unpack ${archive_rel}"
-
-    log "Extracting ${archive_rel} -> ${target_rel}"
-    tar -xzf "${archive_path}" -C "${PROJECT_ROOT}"
-    [[ -f "${sentinel_path}" ]] || die "Archive ${archive_path} did not unpack expected file ${sentinel_path}"
-    chown -R "${RUN_USER}:${RUN_GROUP}" "${target_path}"
-  done
-}
-
 preflight() {
   log "Preflight checks"
   [[ -f "${PROJECT_ROOT}/.env" ]] || die "Missing ${PROJECT_ROOT}/.env"
@@ -249,6 +171,8 @@ build_and_run_compose() {
 install_systemd_units() {
   log "Installing systemd units"
 
+  install -m 0755 "${PROJECT_ROOT}/deploy/systemd/precheck-sdr.sh" /usr/local/bin/dronedetector-precheck-sdr.sh
+
   local src dst
   for src in "${PROJECT_ROOT}"/deploy/systemd/*.service; do
     dst="${SYSTEMD_TARGET_DIR}/$(basename "$src")"
@@ -263,7 +187,7 @@ install_systemd_units() {
   systemctl enable dronedetector-compose.service
   systemctl restart dronedetector-compose.service
 
-  for unit in "${CONFIGURED_SDR_UNITS[@]}"; do
+  for unit in "${SDR_UNITS[@]}"; do
     systemctl enable "$unit"
     systemctl restart "$unit"
   done
@@ -288,7 +212,7 @@ verify_installation() {
   log "Verifying services"
 
   wait_for_systemd_active dronedetector-compose.service 30 || die "dronedetector-compose.service is not active"
-  for unit in "${CONFIGURED_SDR_UNITS[@]}"; do
+  for unit in "${SDR_UNITS[@]}"; do
     wait_for_systemd_active "$unit" 45 || die "$unit is not active"
   done
 
@@ -298,7 +222,7 @@ verify_installation() {
   running_services="$(docker compose -f "$COMPOSE_FILE" ps --status running --services || true)"
 
   printf '%s\n' "$running_services" | grep -Fxq "dronedetector-server-to-master" || die "server_to_master is not running"
-  printf '%s\n' "$running_services" | grep -Fxq "dronedetector-telemetry-server" || die "telemetry_server is not running"
+  printf '%s\n' "$running_services" | grep -Fxq "dronedetector-nn-server" || die "NN_server is not running"
 
   log "Verification completed"
 }
@@ -309,9 +233,7 @@ main() {
   log "Project root: ${PROJECT_ROOT}"
   log "Runtime user: ${RUN_USER}:${RUN_GROUP}"
 
-  extract_local_source_archives
   preflight
-  populate_configured_sdr_units
   install_host_non_python_deps
   setup_sdr_python_env
   install_docker_if_needed

install_all_train.sh

@@ -28,7 +28,7 @@ run_as_root() {
 
 preflight() {
   [[ -f "${PROJECT_ROOT}/deploy/requirements/nn_gpu_pinned.txt" ]] || die "Missing deploy/requirements/nn_gpu_pinned.txt"
-  [[ -f "${PROJECT_ROOT}/requirements-train.txt" ]] || die "Missing train_scripts/requirements-train.txt"
+  [[ -f "${PROJECT_ROOT}/train_scripts/requirements-train.txt" ]] || die "Missing train_scripts/requirements-train.txt"
   [[ -f "${PROJECT_ROOT}/torchsig/pyproject.toml" ]] || die "Missing local torchsig package"
   command -v "${PYTHON_BIN}" >/dev/null 2>&1 || die "${PYTHON_BIN} not found"
 }

logs/analysis.ipynb

@@ -0,0 +1,673 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "215a6c3a",
+   "metadata": {},
+   "source": [
+    "# NN inference analysis\n",
+    "\n",
+    "Анализ CSV с результатами инференса: доля класса `drone`, частоты срабатываний, уверенность модели и интервалы между `drone`-классификациями."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "4e8cff32",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CSV path: /home/sibscience-4/from_ssh/DroneDetector/logs/nn_results_live_6gb.csv\n",
+      "Rows: 27258\n",
+      "Time range: 2026-05-04 17:35:21.019627763+07:00 -> 2026-05-05 12:17:19.369858371+07:00\n",
+      "Missing freq rows: 0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>docker_timestamp</th>\n",
+       "      <th>event_time_iso</th>\n",
+       "      <th>event_time_epoch</th>\n",
+       "      <th>freq</th>\n",
+       "      <th>model_id</th>\n",
+       "      <th>model_type</th>\n",
+       "      <th>prediction</th>\n",
+       "      <th>probability</th>\n",
+       "      <th>ts</th>\n",
+       "      <th>local_time</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2026-05-04T10:35:21.019627763Z</td>\n",
+       "      <td>2026-05-04T17:35:21+07:00</td>\n",
+       "      <td>1.777891e+09</td>\n",
+       "      <td>2400</td>\n",
+       "      <td>2</td>\n",
+       "      <td>ensemble_2400_v44</td>\n",
+       "      <td>drone</td>\n",
+       "      <td>0.99</td>\n",
+       "      <td>2026-05-04 10:35:21.019627763+00:00</td>\n",
+       "      <td>2026-05-04 17:35:21.019627763+07:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2026-05-04T10:35:21.019631281Z</td>\n",
+       "      <td>2026-05-04T17:35:21+07:00</td>\n",
+       "      <td>1.777891e+09</td>\n",
+       "      <td>1200</td>\n",
+       "      <td>1</td>\n",
+       "      <td>ensemble_1200_v44</td>\n",
+       "      <td>noise</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>2026-05-04 10:35:21.019631281+00:00</td>\n",
+       "      <td>2026-05-04 17:35:21.019631281+07:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2026-05-04T10:35:27.048188525Z</td>\n",
+       "      <td>2026-05-04T17:35:27+07:00</td>\n",
+       "      <td>1.777891e+09</td>\n",
+       "      <td>2400</td>\n",
+       "      <td>2</td>\n",
+       "      <td>ensemble_2400_v44</td>\n",
+       "      <td>drone</td>\n",
+       "      <td>0.99</td>\n",
+       "      <td>2026-05-04 10:35:27.048188525+00:00</td>\n",
+       "      <td>2026-05-04 17:35:27.048188525+07:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2026-05-04T10:35:29.238925690Z</td>\n",
+       "      <td>2026-05-04T17:35:29+07:00</td>\n",
+       "      <td>1.777891e+09</td>\n",
+       "      <td>1200</td>\n",
+       "      <td>1</td>\n",
+       "      <td>ensemble_1200_v44</td>\n",
+       "      <td>noise</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>2026-05-04 10:35:29.238925690+00:00</td>\n",
+       "      <td>2026-05-04 17:35:29.238925690+07:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2026-05-04T10:35:32.842234116Z</td>\n",
+       "      <td>2026-05-04T17:35:32+07:00</td>\n",
+       "      <td>1.777891e+09</td>\n",
+       "      <td>2400</td>\n",
+       "      <td>2</td>\n",
+       "      <td>ensemble_2400_v44</td>\n",
+       "      <td>drone</td>\n",
+       "      <td>0.92</td>\n",
+       "      <td>2026-05-04 10:35:32.842234116+00:00</td>\n",
+       "      <td>2026-05-04 17:35:32.842234116+07:00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 docker_timestamp             event_time_iso  \\\n",
+       "0  2026-05-04T10:35:21.019627763Z  2026-05-04T17:35:21+07:00   \n",
+       "1  2026-05-04T10:35:21.019631281Z  2026-05-04T17:35:21+07:00   \n",
+       "2  2026-05-04T10:35:27.048188525Z  2026-05-04T17:35:27+07:00   \n",
+       "3  2026-05-04T10:35:29.238925690Z  2026-05-04T17:35:29+07:00   \n",
+       "4  2026-05-04T10:35:32.842234116Z  2026-05-04T17:35:32+07:00   \n",
+       "\n",
+       "   event_time_epoch  freq  model_id         model_type prediction  \\\n",
+       "0      1.777891e+09  2400         2  ensemble_2400_v44      drone   \n",
+       "1      1.777891e+09  1200         1  ensemble_1200_v44      noise   \n",
+       "2      1.777891e+09  2400         2  ensemble_2400_v44      drone   \n",
+       "3      1.777891e+09  1200         1  ensemble_1200_v44      noise   \n",
+       "4      1.777891e+09  2400         2  ensemble_2400_v44      drone   \n",
+       "\n",
+       "   probability                                  ts  \\\n",
+       "0         0.99 2026-05-04 10:35:21.019627763+00:00   \n",
+       "1         1.00 2026-05-04 10:35:21.019631281+00:00   \n",
+       "2         0.99 2026-05-04 10:35:27.048188525+00:00   \n",
+       "3         1.00 2026-05-04 10:35:29.238925690+00:00   \n",
+       "4         0.92 2026-05-04 10:35:32.842234116+00:00   \n",
+       "\n",
+       "                           local_time  \n",
+       "0 2026-05-04 17:35:21.019627763+07:00  \n",
+       "1 2026-05-04 17:35:21.019631281+07:00  \n",
+       "2 2026-05-04 17:35:27.048188525+07:00  \n",
+       "3 2026-05-04 17:35:29.238925690+07:00  \n",
+       "4 2026-05-04 17:35:32.842234116+07:00  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from pathlib import Path\n",
+    "import pandas as pd\n",
+    "\n",
+    "csv_path = Path('/home/sibscience-4/from_ssh/DroneDetector/logs/nn_results_live_6gb.csv')\n",
+    "df = pd.read_csv(csv_path)\n",
+    "\n",
+    "df['ts'] = pd.to_datetime(df['docker_timestamp'], utc=True)\n",
+    "df['local_time'] = df['ts'].dt.tz_convert('Asia/Novosibirsk')\n",
+    "df['freq'] = pd.to_numeric(df['freq'], errors='coerce').astype('Int64')\n",
+    "df['probability'] = pd.to_numeric(df['probability'], errors='coerce')\n",
+    "df = df.sort_values('ts').reset_index(drop=True)\n",
+    "\n",
+    "print(f'CSV path: {csv_path}')\n",
+    "print(f'Rows: {len(df)}')\n",
+    "print(f'Time range: {df[\"local_time\"].min()} -> {df[\"local_time\"].max()}')\n",
+    "print(f'Missing freq rows: {df[\"freq\"].isna().sum()}')\n",
+    "display(df.head())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0fcc6dd6",
+   "metadata": {},
+   "source": [
+    "## Общая сводка по частотам и классам"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "7bf0fc3f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>freq</th>\n",
+       "      <th>prediction</th>\n",
+       "      <th>count</th>\n",
+       "      <th>avg_probability</th>\n",
+       "      <th>min_probability</th>\n",
+       "      <th>max_probability</th>\n",
+       "      <th>freq_total</th>\n",
+       "      <th>class_rate</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1200</td>\n",
+       "      <td>drone</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.840000</td>\n",
+       "      <td>0.78</td>\n",
+       "      <td>0.91</td>\n",
+       "      <td>13632</td>\n",
+       "      <td>0.000220</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1200</td>\n",
+       "      <td>noise</td>\n",
+       "      <td>13629</td>\n",
+       "      <td>0.997436</td>\n",
+       "      <td>0.91</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>13632</td>\n",
+       "      <td>0.999780</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2400</td>\n",
+       "      <td>drone</td>\n",
+       "      <td>11921</td>\n",
+       "      <td>0.868013</td>\n",
+       "      <td>0.50</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>13626</td>\n",
+       "      <td>0.874872</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2400</td>\n",
+       "      <td>noise</td>\n",
+       "      <td>1705</td>\n",
+       "      <td>0.649185</td>\n",
+       "      <td>0.50</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>13626</td>\n",
+       "      <td>0.125128</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   freq prediction  count  avg_probability  min_probability  max_probability  \\\n",
+       "0  1200      drone      3         0.840000             0.78             0.91   \n",
+       "1  1200      noise  13629         0.997436             0.91             1.00   \n",
+       "2  2400      drone  11921         0.868013             0.50             1.00   \n",
+       "3  2400      noise   1705         0.649185             0.50             1.00   \n",
+       "\n",
+       "   freq_total  class_rate  \n",
+       "0       13632    0.000220  \n",
+       "1       13632    0.999780  \n",
+       "2       13626    0.874872  \n",
+       "3       13626    0.125128  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class_summary = (\n",
+    "    df.groupby(['freq', 'prediction'], dropna=False)\n",
+    "      .agg(\n",
+    "          count=('prediction', 'size'),\n",
+    "          avg_probability=('probability', 'mean'),\n",
+    "          min_probability=('probability', 'min'),\n",
+    "          max_probability=('probability', 'max'),\n",
+    "      )\n",
+    "      .reset_index()\n",
+    ")\n",
+    "\n",
+    "freq_total = df.groupby('freq', dropna=False).size().rename('freq_total').reset_index()\n",
+    "class_summary = class_summary.merge(freq_total, on='freq', how='left')\n",
+    "class_summary['class_rate'] = class_summary['count'] / class_summary['freq_total']\n",
+    "class_summary = class_summary.sort_values(['freq', 'prediction']).reset_index(drop=True)\n",
+    "\n",
+    "display(class_summary)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "039fcfa6",
+   "metadata": {},
+   "source": [
+    "## Статистика по классу drone"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "c1ed2bc4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>freq</th>\n",
+       "      <th>total_inferences</th>\n",
+       "      <th>drone_count</th>\n",
+       "      <th>avg_drone_probability</th>\n",
+       "      <th>median_drone_probability</th>\n",
+       "      <th>min_drone_probability</th>\n",
+       "      <th>max_drone_probability</th>\n",
+       "      <th>first_drone_time</th>\n",
+       "      <th>last_drone_time</th>\n",
+       "      <th>drone_rate</th>\n",
+       "      <th>dataset_duration_min</th>\n",
+       "      <th>drone_per_min</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1200</td>\n",
+       "      <td>13632</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.840000</td>\n",
+       "      <td>0.83</td>\n",
+       "      <td>0.78</td>\n",
+       "      <td>0.91</td>\n",
+       "      <td>2026-05-05 03:18:55.374394280+07:00</td>\n",
+       "      <td>2026-05-05 08:39:23.676669045+07:00</td>\n",
+       "      <td>0.000220</td>\n",
+       "      <td>1121.972504</td>\n",
+       "      <td>0.002674</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2400</td>\n",
+       "      <td>13626</td>\n",
+       "      <td>11921</td>\n",
+       "      <td>0.868013</td>\n",
+       "      <td>0.93</td>\n",
+       "      <td>0.50</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>2026-05-04 17:35:21.019627763+07:00</td>\n",
+       "      <td>2026-05-05 12:17:19.369858371+07:00</td>\n",
+       "      <td>0.874872</td>\n",
+       "      <td>1121.972504</td>\n",
+       "      <td>10.625038</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   freq  total_inferences  drone_count  avg_drone_probability  \\\n",
+       "0  1200             13632            3               0.840000   \n",
+       "1  2400             13626        11921               0.868013   \n",
+       "\n",
+       "   median_drone_probability  min_drone_probability  max_drone_probability  \\\n",
+       "0                      0.83                   0.78                   0.91   \n",
+       "1                      0.93                   0.50                   1.00   \n",
+       "\n",
+       "                     first_drone_time                     last_drone_time  \\\n",
+       "0 2026-05-05 03:18:55.374394280+07:00 2026-05-05 08:39:23.676669045+07:00   \n",
+       "1 2026-05-04 17:35:21.019627763+07:00 2026-05-05 12:17:19.369858371+07:00   \n",
+       "\n",
+       "   drone_rate  dataset_duration_min  drone_per_min  \n",
+       "0    0.000220           1121.972504       0.002674  \n",
+       "1    0.874872           1121.972504      10.625038  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "drone = df[df['prediction'].eq('drone')].copy()\n",
+    "\n",
+    "total_by_freq = df.groupby('freq', dropna=False).size().rename('total_inferences')\n",
+    "drone_by_freq = drone.groupby('freq', dropna=False).agg(\n",
+    "    drone_count=('prediction', 'size'),\n",
+    "    avg_drone_probability=('probability', 'mean'),\n",
+    "    median_drone_probability=('probability', 'median'),\n",
+    "    min_drone_probability=('probability', 'min'),\n",
+    "    max_drone_probability=('probability', 'max'),\n",
+    "    first_drone_time=('local_time', 'min'),\n",
+    "    last_drone_time=('local_time', 'max'),\n",
+    ")\n",
+    "\n",
+    "drone_stats = total_by_freq.to_frame().join(drone_by_freq, how='left').fillna({'drone_count': 0})\n",
+    "drone_stats['drone_count'] = drone_stats['drone_count'].astype(int)\n",
+    "drone_stats['drone_rate'] = drone_stats['drone_count'] / drone_stats['total_inferences']\n",
+    "\n",
+    "if len(df) > 1:\n",
+    "    duration_min = (df['ts'].max() - df['ts'].min()).total_seconds() / 60\n",
+    "else:\n",
+    "    duration_min = 0\n",
+    "\n",
+    "drone_stats['dataset_duration_min'] = duration_min\n",
+    "drone_stats['drone_per_min'] = drone_stats['drone_count'] / duration_min if duration_min > 0 else 0\n",
+    "drone_stats = drone_stats.reset_index().sort_values('freq').reset_index(drop=True)\n",
+    "\n",
+    "display(drone_stats)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "56ae5e2b",
+   "metadata": {},
+   "source": [
+    "## Интервалы между drone-классификациями"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "0c43eb07",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>freq</th>\n",
+       "      <th>interval_count</th>\n",
+       "      <th>avg_interval_sec</th>\n",
+       "      <th>median_interval_sec</th>\n",
+       "      <th>min_interval_sec</th>\n",
+       "      <th>max_interval_sec</th>\n",
+       "      <th>p90_interval_sec</th>\n",
+       "      <th>p95_interval_sec</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1200</td>\n",
+       "      <td>2</td>\n",
+       "      <td>9614.151137</td>\n",
+       "      <td>9614.151137</td>\n",
+       "      <td>619.196112</td>\n",
+       "      <td>18609.106163</td>\n",
+       "      <td>16810.115158</td>\n",
+       "      <td>17709.610661</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2400</td>\n",
+       "      <td>11920</td>\n",
+       "      <td>5.647513</td>\n",
+       "      <td>4.974157</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>1210.107950</td>\n",
+       "      <td>9.203728</td>\n",
+       "      <td>10.079097</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   freq  interval_count  avg_interval_sec  median_interval_sec  \\\n",
+       "0  1200               2       9614.151137          9614.151137   \n",
+       "1  2400           11920          5.647513             4.974157   \n",
+       "\n",
+       "   min_interval_sec  max_interval_sec  p90_interval_sec  p95_interval_sec  \n",
+       "0        619.196112      18609.106163      16810.115158      17709.610661  \n",
+       "1          0.000000       1210.107950          9.203728         10.079097  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "if drone.empty:\n",
+    "    print('No drone predictions found')\n",
+    "    drone_interval_stats = pd.DataFrame()\n",
+    "else:\n",
+    "    drone = drone.sort_values(['freq', 'ts']).copy()\n",
+    "    drone['dt_drone_freq_sec'] = drone.groupby('freq')['ts'].diff().dt.total_seconds()\n",
+    "    drone_interval_stats = (\n",
+    "        drone.groupby('freq', dropna=False)['dt_drone_freq_sec']\n",
+    "             .agg(\n",
+    "                 interval_count='count',\n",
+    "                 avg_interval_sec='mean',\n",
+    "                 median_interval_sec='median',\n",
+    "                 min_interval_sec='min',\n",
+    "                 max_interval_sec='max',\n",
+    "                 p90_interval_sec=lambda s: s.quantile(0.90),\n",
+    "                 p95_interval_sec=lambda s: s.quantile(0.95),\n",
+    "             )\n",
+    "             .reset_index()\n",
+    "    )\n",
+    "    display(drone_interval_stats)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2ecf96f0",
+   "metadata": {},
+   "source": [
+    "## Drone-события"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff14a339",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "drone_events = drone[[\n",
+    "    'local_time',\n",
+    "    'docker_timestamp',\n",
+    "    'freq',\n",
+    "    'model_id',\n",
+    "    'model_type',\n",
+    "    'prediction',\n",
+    "    'probability',\n",
+    "]].sort_values('local_time').reset_index(drop=True)\n",
+    "\n",
+    "display(drone_events.head(50))\n",
+    "display(drone_events.tail(50))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "376b84d0",
+   "metadata": {},
+   "source": [
+    "## Частота drone-классификаций по минутам"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5f82f5c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if drone.empty:\n",
+    "    print('No drone predictions found')\n",
+    "else:\n",
+    "    drone_per_minute = (\n",
+    "        drone.set_index('local_time')\n",
+    "             .groupby('freq')\n",
+    "             .resample('1min')\n",
+    "             .size()\n",
+    "             .rename('drone_count')\n",
+    "             .reset_index()\n",
+    "    )\n",
+    "    display(drone_per_minute.tail(100))\n",
+    "\n",
+    "    pivot = drone_per_minute.pivot_table(\n",
+    "        index='local_time',\n",
+    "        columns='freq',\n",
+    "        values='drone_count',\n",
+    "        fill_value=0,\n",
+    "    )\n",
+    "    display(pivot.tail(50))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ad570d05",
+   "metadata": {},
+   "source": [
+    "## Быстрые графики"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "895550a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "if not drone.empty:\n",
+    "    ax = drone_stats.set_index('freq')['drone_rate'].plot(kind='bar', figsize=(8, 4), title='Drone rate by frequency')\n",
+    "    ax.set_ylabel('drone_count / total_inferences')\n",
+    "    plt.show()\n",
+    "\n",
+    "    ax = drone.boxplot(column='probability', by='freq', figsize=(8, 4))\n",
+    "    ax.set_title('Drone probability by frequency')\n",
+    "    ax.set_xlabel('freq')\n",
+    "    ax.set_ylabel('probability')\n",
+    "    plt.suptitle('')\n",
+    "    plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

orange_scripts/compose_send_data_5800.py

@@ -1,115 +0,0 @@
-
-from common.runtime import load_root_env, validate_env, as_float, as_int, as_str
-import numpy as np
-import requests
-import os
-import sys
-import json
-import time
-
-
-load_root_env(__file__)
-validate_env("orange_scripts/compose_send_data_5800.py", {
-    "POROG_5800": as_float,
-    "SERVER_IP_2": as_str,
-    "SERVER_PORT_2": as_int,
-})
-porog = float(os.getenv('POROG_5800'))
-server_ip_1 = os.getenv('SERVER_IP_1')
-server_port_1 = os.getenv('SERVER_PORT_1')
-server_ip_2 = os.getenv('SERVER_IP_2')
-server_port_2 = os.getenv('SERVER_PORT_2')
-PARAMS = {'split_size': 400_000, 'point_amount': 100_000}
-PARAMS['show_amount'] = 0.8 * PARAMS['point_amount']
-token = 0
-channel = 1
-flag = 0
-
-##############################
-# HYPERPARAMETERS
-##############################
-f_base = 5.9e9
-f_step = 20e6
-f_roof = 5.7e9
-##############################
-# Variables
-##############################
-f = f_base
-EOCF = 0
-signal_arr = []
-
-
-class NumpyArrayEncoder(json.JSONEncoder):
-    def default(self, obj):
-        if isinstance(obj, np.integer):
-            return int(obj)
-        elif isinstance(obj, np.ndarray):
-            return obj.tolist()
-        else:
-            return super(NumpyArrayEncoder, self).default(obj)
-
-
-def send_data(sig):
-    try:
-        global token
-        print('#' * 10)
-        print('\nОтправка пакета ' + str(token+1))
-        data_to_send = {
-            "freq": 5800,
-            "channel": int(channel),
-            "token": int(token+1),
-            "data_real": np.asarray(np.array(sig, dtype=np.complex64).real, dtype=np.float32),
-            "data_imag": np.asarray(np.array(sig, dtype=np.complex64).imag, dtype=np.float32)
-        }
-        mod_data_to_send = json.dumps(data_to_send, cls=NumpyArrayEncoder)
-        response = requests.post("http://{0}:{1}/receive_data".format(server_ip_2, server_port_2), json=mod_data_to_send)
-        if response.status_code == 200:
-            token += 1
-            print(response.text)
-            print('#' * 10)       
-        else:
-            print("Ошибка при отправке данных: ", response.status_code)
-            print('#' * 10)
-    except Exception as exc:
-        print(str(exc))
-
-
-def median(sig):
-    global flag
-    median = abs(float(np.median(sorted(np.asarray(np.abs(np.array(sig, dtype=np.complex64)), dtype=np.float32))[int(PARAMS['show_amount']):])))
-    flag = 0 if porog > median else 1
-    print(channel, median, flag)
-
-
-def work(lvl):
-    global flag
-    global channel
-    global f_base
-    global f_step
-    global f_roof
-    global f
-    global EOCF
-    global signal_arr
-
-    y = np.array(lvl).ravel()
-    signal_arr = np.concatenate((signal_arr, y), axis=None)
-
-    if f >= f_roof:
-        f = f_base
-        signal_arr = []
-        channel = 1
-        return f, EOCF
-    else:
-        if flag == 0 and len(signal_arr) >= PARAMS['point_amount']:
-            median(signal_arr[:PARAMS['point_amount']])
-            signal_arr = []
-            if flag == 0:
-                f += f_step
-                channel += 1
-        if len(signal_arr) >= PARAMS['split_size']:
-            send_data(signal_arr[:PARAMS['split_size']])
-            flag = 0
-            signal_arr = []
-            channel += 1
-            f += f_step
-        return f, EOCF

orange_scripts/main_2400.py

@@ -67,8 +67,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(samp_rate)
         self.rtlsdr_source_0.set_center_freq(center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(0, 0)
+        self.rtlsdr_source_0.set_if_gain(0, 0)
         self.rtlsdr_source_0.set_bb_gain(0, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

orange_scripts/main_5800.py

@@ -1,172 +0,0 @@
-from gnuradio import blocks, gr
-import sys
-import signal
-import compose_send_data_5800 as my_freq
-import osmosdr
-import time
-import threading
-import subprocess
-import os
-from common.runtime import load_root_env, resolve_hackrf_index
-
-
-load_root_env(__file__)
-
-def get_hack_id():
-    return resolve_hackrf_index('HACKID_5800', 'orange_scripts/main_5800.py')
-    serial_number = os.getenv('HACKID_5800')
-    pos = None
-    output = []
-    try:
-        command = 'lsusb -v -d 1d50:6089 | grep iSerial'
-        output.append(subprocess.check_output(command, shell=True, text=True))
-    except subprocess.CalledProcessError as e:
-        print(f"Команда завершилась с кодом возврата {e.returncode}")
-        print(e)
-    print(output)
-    output_lines = output[0].strip().split('\n')
-    print(output_lines)
-    serial_numbers = [line.split()[-1] for line in output_lines]
-    print(serial_numbers)
-    for i, number in enumerate(serial_numbers):
-        if number == serial_number:
-            id = i
-            break
-    if id is not None:
-        print('HackId is: {0}'.format(id))
-        return str(id)
-    else:
-        print('Такого хака нет!')
-
-
-class get_center_freq(gr.top_block):
-
-    def __init__(self):
-        gr.top_block.__init__(self, "get_center_freq")
-
-        ##################################################
-        # Variables
-        ##################################################
-        self.prob_freq = prob_freq = 0
-        self.top_peaks_amount = top_peaks_amount = 20
-        self.samp_rate = samp_rate = 20e6
-        self.poll_rate = poll_rate = 10000
-        self.num_points = num_points = 8192
-        self.flag = flag = 1
-        self.decimation = decimation = 1
-        self.center_freq = center_freq = my_freq.work(prob_freq)[0]
-
-        ##################################################
-        # Blocks
-        ##################################################
-        self.probSigVec = blocks.probe_signal_vc(4096)
-        self.rtlsdr_source_0 = osmosdr.source(
-            args="numchan=" + str(1) + " " + 'hackrf=' + get_hack_id()
-        )
-        self.rtlsdr_source_0.set_time_unknown_pps(osmosdr.time_spec_t())
-        self.rtlsdr_source_0.set_sample_rate(samp_rate)
-        self.rtlsdr_source_0.set_center_freq(center_freq, 0)
-        self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
-        self.rtlsdr_source_0.set_bb_gain(0, 0)
-        self.rtlsdr_source_0.set_antenna('', 0)
-        self.rtlsdr_source_0.set_bandwidth(0, 0)
-        self.rtlsdr_source_0.set_min_output_buffer(4096)
-
-        def _prob_freq_probe():
-            while True:
-
-                val = self.probSigVec.level()
-                try:
-                    self.set_prob_freq(val)
-                except AttributeError:
-                    pass
-                time.sleep(1.0 / (poll_rate))
-        _prob_freq_thread = threading.Thread(target=_prob_freq_probe)
-        _prob_freq_thread.daemon = True
-        _prob_freq_thread.start()
-
-        self.blocks_stream_to_vector_1 = blocks.stream_to_vector(gr.sizeof_gr_complex*1, 4096)
-
-
-
-        ##################################################
-        # Connections
-        ##################################################
-        self.connect((self.blocks_stream_to_vector_1, 0), (self.probSigVec, 0))
-        self.connect((self.rtlsdr_source_0, 0), (self.blocks_stream_to_vector_1, 0))
-
-    def get_prob_freq(self):
-        return self.prob_freq
-
-    def set_prob_freq(self, prob_freq):
-        self.prob_freq = prob_freq
-        self.set_center_freq(my_freq.work(self.prob_freq)[0])
-
-    def get_top_peaks_amount(self):
-        return self.top_peaks_amount
-
-    def set_top_peaks_amount(self, top_peaks_amount):
-        self.top_peaks_amount = top_peaks_amount
-
-    def get_samp_rate(self):
-        return self.samp_rate
-
-    def set_samp_rate(self, samp_rate):
-        self.samp_rate = samp_rate
-        self.rtlsdr_source_0.set_sample_rate(self.samp_rate)
-
-    def get_poll_rate(self):
-        return self.poll_rate
-
-    def set_poll_rate(self, poll_rate):
-        self.poll_rate = poll_rate
-
-    def get_num_points(self):
-        return self.num_points
-
-    def set_num_points(self, num_points):
-        self.num_points = num_points
-
-    def get_flag(self):
-        return self.flag
-
-    def set_flag(self, flag):
-        self.flag = flag
-
-    def get_decimation(self):
-        return self.decimation
-
-    def set_decimation(self, decimation):
-        self.decimation = decimation
-
-    def get_center_freq(self):
-        return self.center_freq
-
-    def set_center_freq(self, center_freq):
-        self.center_freq = center_freq
-        self.rtlsdr_source_0.set_center_freq(self.center_freq, 0)
-
-
-def main(top_block_cls=get_center_freq, options=None):
-    time.sleep(3)
-    tb = top_block_cls()
-    def sig_handler(sig=None, frame=None):
-        tb.stop()
-        tb.wait()
-        sys.exit(0)
-
-    signal.signal(signal.SIGINT, sig_handler)
-    signal.signal(signal.SIGTERM, sig_handler)
-
-    tb.start()
-    try:
-        input('Press Enter to quit: ')
-    except EOFError:
-        pass
-    tb.wait()
-
-
-if __name__ == '__main__':
-    main()

read_energy.py

@@ -69,7 +69,7 @@ class ProbeTop(gr.top_block):
             try:
                 getattr(self.src, fn)(val, 0)
             except Exception:
-                raise Exception("не ставится  усиление")
+                pass
         try:
             self.src.set_bandwidth(0, 0)
         except Exception:
@@ -260,7 +260,7 @@ def build_parser() -> argparse.ArgumentParser:
     p.add_argument("--interval", type=float, default=0.5, help="Per-device read interval (s)")
     p.add_argument("--refresh", type=float, default=0.5, help="Console refresh interval (s)")
     p.add_argument("--reopen-delay", type=float, default=1.0, help="Retry delay after BUSY/ERR (s)")
-    p.add_argument("--gain", type=float, default=0.0, help="General gain")
+    p.add_argument("--gain", type=float, default=16.0, help="General gain")
     p.add_argument("--if-gain", type=float, default=16.0, help="IF gain")
     p.add_argument("--bb-gain", type=float, default=16.0, help="BB gain")
     return p

read_energy_wide.py

@@ -1,807 +0,0 @@
-"""
-./.venv-sdr/bin/python read_energy_wide.py \
-    --serial 0000000000000000a18c63dc2a83b813 \
-    --sample-rate 20000000 \
-    --base 6000 \
-    --roof 5700 \
-    --step 20
-
-"""
-#!/usr/bin/env python3
-import argparse
-import math
-import re
-import signal
-import subprocess
-import sys
-import time
-from dataclasses import dataclass
-from typing import Dict, List, Optional, Tuple
-
-try:
-    import numpy as np
-except Exception as exc:
-    print(f"numpy import failed: {exc}", file=sys.stderr)
-    sys.exit(1)
-
-try:
-    from gnuradio import blocks, gr
-    import osmosdr
-except Exception as exc:
-    print(f"gnuradio/osmosdr import failed: {exc}", file=sys.stderr)
-    print("Run with the SDR venv, e.g. .venv-sdr/bin/python read_energy_wide.py", file=sys.stderr)
-    sys.exit(1)
-
-EPS = 1e-20
-
-
-@dataclass
-class ScanWindow:
-    seq: int
-    start_mhz: float
-    end_mhz: float
-    low_mhz: float
-    high_mhz: float
-    center_mhz: float
-    status: str = "INIT"
-    rms: Optional[float] = None
-    power_lin: Optional[float] = None
-    dbfs: Optional[float] = None
-    samples: int = 0
-    updated_at: float = 0.0
-    error: str = ""
-    pass_no: int = 0
-
-
-class WideProbeTop(gr.top_block):
-    def __init__(
-        self,
-        index: int,
-        center_freq_hz: float,
-        sample_rate: float,
-        vec_len: int,
-        gain: float,
-        if_gain: float,
-        bb_gain: float,
-    ):
-        super().__init__("hackrf_energy_wide_probe")
-        self.probe = blocks.probe_signal_vc(vec_len)
-        self.stream_to_vec = blocks.stream_to_vector(gr.sizeof_gr_complex * 1, vec_len)
-        self.src = osmosdr.source(args=f"numchan=1 hackrf={index}")
-        self.src.set_time_unknown_pps(osmosdr.time_spec_t())
-        self.src.set_sample_rate(sample_rate)
-        self.src.set_center_freq(center_freq_hz, 0)
-        try:
-            self.src.set_freq_corr(0, 0)
-        except Exception:
-            pass
-        try:
-            self.src.set_gain_mode(False, 0)
-        except Exception:
-            pass
-        for fn, val in (("set_gain", gain), ("set_if_gain", if_gain), ("set_bb_gain", bb_gain)):
-            try:
-                getattr(self.src, fn)(val, 0)
-            except Exception:
-                pass
-        try:
-            self.src.set_bandwidth(0, 0)
-        except Exception:
-            pass
-        try:
-            self.src.set_antenna("", 0)
-        except Exception:
-            pass
-        self.connect((self.src, 0), (self.stream_to_vec, 0))
-        self.connect((self.stream_to_vec, 0), (self.probe, 0))
-
-    def tune(self, freq_hz: float) -> None:
-        self.src.set_center_freq(freq_hz, 0)
-
-    def read_metrics(self) -> Tuple[float, float, float, int]:
-        arr = np.asarray(self.probe.level(), dtype=np.complex64)
-        if arr.size == 0:
-            raise RuntimeError("no samples")
-        power_lin = float(np.mean(arr.real * arr.real + arr.imag * arr.imag))
-        rms = math.sqrt(max(power_lin, 0.0))
-        dbfs = 10.0 * math.log10(max(power_lin, EPS))
-        return rms, power_lin, dbfs, int(arr.size)
-
-    def read_window(self, settle: float, avg_reads: int, pause_between_reads: float) -> Tuple[float, float, float, int]:
-        if settle > 0:
-            time.sleep(settle)
-
-        read_count = max(1, avg_reads)
-        powers: List[float] = []
-        sample_sizes: List[int] = []
-        last_error: Optional[Exception] = None
-
-        for idx in range(read_count):
-            deadline = time.time() + 1.0
-            while True:
-                try:
-                    _, power_lin, _, samples = self.read_metrics()
-                    powers.append(power_lin)
-                    sample_sizes.append(samples)
-                    break
-                except Exception as exc:
-                    last_error = exc
-                    if time.time() >= deadline:
-                        raise RuntimeError(str(last_error) if last_error else "no samples")
-                    time.sleep(0.02)
-            if idx + 1 < read_count and pause_between_reads > 0:
-                time.sleep(pause_between_reads)
-
-        power_lin = float(sum(powers) / len(powers))
-        rms = math.sqrt(max(power_lin, 0.0))
-        dbfs = 10.0 * math.log10(max(power_lin, EPS))
-        samples = int(sum(sample_sizes) / len(sample_sizes))
-        return rms, power_lin, dbfs, samples
-
-
-def parse_hackrf_info() -> Dict[str, int]:
-    try:
-        proc = subprocess.run(["hackrf_info"], capture_output=True, text=True, timeout=15)
-    except FileNotFoundError:
-        raise RuntimeError("hackrf_info not found")
-    except subprocess.TimeoutExpired:
-        raise RuntimeError("hackrf_info timeout")
-    text = (proc.stdout or "") + "\n" + (proc.stderr or "")
-    out: Dict[str, int] = {}
-    cur_idx: Optional[int] = None
-    for line in text.splitlines():
-        m = re.search(r"^Index:\s*(\d+)", line)
-        if m:
-            cur_idx = int(m.group(1))
-            continue
-        m = re.search(r"^Serial number:\s*([0-9a-fA-F]+)", line)
-        if m and cur_idx is not None:
-            out[m.group(1).lower()] = cur_idx
-    if not out:
-        raise RuntimeError("no devices parsed from hackrf_info")
-    return out
-
-
-def fmt(value: Optional[float], spec: str) -> str:
-    return "-" if value is None else format(value, spec)
-
-
-def build_windows(base_mhz: float, roof_mhz: float, step_mhz: float) -> List[ScanWindow]:
-    if step_mhz <= 0:
-        raise ValueError("step must be > 0")
-    if base_mhz == roof_mhz:
-        raise ValueError("base and roof must be different")
-
-    direction = -1.0 if roof_mhz < base_mhz else 1.0
-    edge = base_mhz
-    seq = 1
-    windows: List[ScanWindow] = []
-
-    while True:
-        next_edge = edge + direction * step_mhz
-        if direction < 0 and next_edge < roof_mhz:
-            next_edge = roof_mhz
-        if direction > 0 and next_edge > roof_mhz:
-            next_edge = roof_mhz
-
-        low_mhz = min(edge, next_edge)
-        high_mhz = max(edge, next_edge)
-        center_mhz = (low_mhz + high_mhz) / 2.0
-        windows.append(
-            ScanWindow(
-                seq=seq,
-                start_mhz=edge,
-                end_mhz=next_edge,
-                low_mhz=low_mhz,
-                high_mhz=high_mhz,
-                center_mhz=center_mhz,
-            )
-        )
-
-        if next_edge == roof_mhz:
-            break
-        edge = next_edge
-        seq += 1
-
-    return windows
-
-
-def render(
-    windows: List[ScanWindow],
-    serial: str,
-    index: int,
-    sample_rate: float,
-    base_mhz: float,
-    roof_mhz: float,
-    step_mhz: float,
-    started_at: float,
-    pass_no: int,
-    current_seq: int,
-) -> None:
-    now = time.time()
-    capture_bw_mhz = sample_rate / 1e6
-    current_row = next((row for row in windows if row.seq == current_seq), None)
-    best_row = max(
-        (row for row in windows if row.status == "OK" and row.dbfs is not None),
-        key=lambda row: row.dbfs if row.dbfs is not None else float("-inf"),
-        default=None,
-    )
-    print("\x1b[2J\x1b[H", end="")
-    print("HackRF Wide Energy Monitor (relative power: RMS / linear / dBFS)")
-    print(
-        f"serial: {serial} | idx: {index} | sample-rate: {capture_bw_mhz:.3f} MHz | "
-        f"scan: {base_mhz:.3f}->{roof_mhz:.3f} MHz step {step_mhz:.3f} MHz | "
-        f"pass: {pass_no} | uptime: {int(now-started_at)}s | {time.strftime('%Y-%m-%d %H:%M:%S')}"
-    )
-    print()
-    header = (
-        f"{'cur':>3} {'seq':>3} {'window MHz':>23} {'center':>9} {'status':>8} "
-        f"{'dBFS':>9} {'rms':>10} {'power':>12} {'N':>5} {'age':>5}  error"
-    )
-    print(header)
-    print("-" * len(header))
-    for row in windows:
-        age = "-" if row.updated_at <= 0 else f"{(now-row.updated_at):.1f}"
-        err = row.error
-        if len(err) > 50:
-            err = err[:47] + "..."
-        marker = ">>>" if row.seq == current_seq else ""
-        print(
-            f"{marker:>3} {row.seq:>3} "
-            f"{f'{row.high_mhz:.3f}-{row.low_mhz:.3f}':>23} {row.center_mhz:>9.3f} {row.status:>8} "
-            f"{fmt(row.dbfs, '.2f'):>9} {fmt(row.rms, '.6f'):>10} {fmt(row.power_lin, '.8f'):>12} "
-            f"{row.samples:>5} {age:>5}  {err}"
-        )
-    print()
-    if best_row is not None:
-        best_age = "-" if best_row.updated_at <= 0 else f"{(now-best_row.updated_at):.1f}"
-        print(
-            f"{'':>3} {'MAX':>3} "
-            f"{f'{best_row.high_mhz:.3f}-{best_row.low_mhz:.3f}':>23} {best_row.center_mhz:>9.3f} {best_row.status:>8} "
-            f"{fmt(best_row.dbfs, '.2f'):>9} {fmt(best_row.rms, '.6f'):>10} {fmt(best_row.power_lin, '.8f'):>12} "
-            f"{best_row.samples:>5} {best_age:>5}  pass={best_row.pass_no}"
-        )
-    elif current_row is not None:
-        current_age = "-" if current_row.updated_at <= 0 else f"{(now-current_row.updated_at):.1f}"
-        print(
-            f"{'':>3} {'MAX':>3} "
-            f"{f'{current_row.high_mhz:.3f}-{current_row.low_mhz:.3f}':>23} {current_row.center_mhz:>9.3f} {'INIT':>8} "
-            f"{fmt(None, '.2f'):>9} {fmt(None, '.6f'):>10} {fmt(None, '.8f'):>12} "
-            f"{0:>5} {current_age:>5}  no successful windows yet"
-        )
-    print("Ctrl+C to stop. Window width equals step; sample-rate must be >= step to cover each window.")
-    sys.stdout.flush()
-
-
-def build_parser() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(description="Retune one HackRF across a wide frequency range and measure energy")
-    parser.add_argument("--serial", required=True, help="HackRF serial number from hackrf_info")
-    parser.add_argument("--sample-rate", type=float, required=True, help="Sample rate in Hz")
-    parser.add_argument("--base", type=float, required=True, help="Scan start edge in MHz")
-    parser.add_argument("--roof", type=float, required=True, help="Scan end edge in MHz")
-    parser.add_argument("--step", type=float, required=True, help="Window width / retune step in MHz")
-    parser.add_argument("--vec-len", type=int, default=4096, help="Probe vector length")
-    parser.add_argument("--settle", type=float, default=0.12, help="Wait time after retune before reading (s)")
-    parser.add_argument("--avg-reads", type=int, default=3, help="How many probe reads to average per window")
-    parser.add_argument("--pause-between-reads", type=float, default=0.02, help="Pause between averaged reads (s)")
-    parser.add_argument("--passes", type=int, default=0, help="Number of sweep passes, 0 means infinite")
-    parser.add_argument("--gain", type=float, default=16.0, help="General gain")
-    parser.add_argument("--if-gain", type=float, default=16.0, help="IF gain")
-    parser.add_argument("--bb-gain", type=float, default=16.0, help="BB gain")
-    return parser
-
-
-def main() -> int:
-    args = build_parser().parse_args()
-    serial = args.serial.lower()
-
-    try:
-        windows = build_windows(args.base, args.roof, args.step)
-    except ValueError as exc:
-        print(f"invalid scan range: {exc}", file=sys.stderr)
-        return 2
-
-    step_hz = args.step * 1e6
-    if args.sample_rate < step_hz:
-        print(
-            f"sample-rate {args.sample_rate:.0f} Hz is smaller than step window {step_hz:.0f} Hz; "
-            "this would leave gaps in the scan",
-            file=sys.stderr,
-        )
-        return 2
-
-    try:
-        serial_to_index = parse_hackrf_info()
-    except Exception as exc:
-        print(f"hackrf discovery failed: {exc}", file=sys.stderr)
-        return 3
-
-    index = serial_to_index.get(serial)
-    if index is None:
-        print(f"serial {serial} not found in hackrf_info", file=sys.stderr)
-        print("available serials:", file=sys.stderr)
-        for item_serial, item_index in sorted(serial_to_index.items(), key=lambda item: item[1]):
-            print(f"  idx={item_index} serial={item_serial}", file=sys.stderr)
-        return 4
-
-    stop_requested = False
-
-    def on_signal(signum, frame):
-        nonlocal stop_requested
-        stop_requested = True
-
-    signal.signal(signal.SIGINT, on_signal)
-    signal.signal(signal.SIGTERM, on_signal)
-
-    probe: Optional[WideProbeTop] = None
-    started_at = time.time()
-    pass_no = 0
-    current_seq = windows[0].seq
-
-    try:
-        probe = WideProbeTop(
-            index=index,
-            center_freq_hz=windows[0].center_mhz * 1e6,
-            sample_rate=args.sample_rate,
-            vec_len=args.vec_len,
-            gain=args.gain,
-            if_gain=args.if_gain,
-            bb_gain=args.bb_gain,
-        )
-        probe.start()
-        time.sleep(max(args.settle, 0.12))
-
-        while not stop_requested:
-            pass_no += 1
-            for row in windows:
-                if stop_requested:
-                    break
-                current_seq = row.seq
-                try:
-                    probe.tune(row.center_mhz * 1e6)
-                    rms, power_lin, dbfs, samples = probe.read_window(
-                        settle=args.settle,
-                        avg_reads=args.avg_reads,
-                        pause_between_reads=args.pause_between_reads,
-                    )
-                    row.status = "OK"
-                    row.rms = rms
-                    row.power_lin = power_lin
-                    row.dbfs = dbfs
-                    row.samples = samples
-                    row.error = ""
-                    row.updated_at = time.time()
-                    row.pass_no = pass_no
-                except Exception as exc:
-                    row.status = "ERR"
-                    row.error = str(exc)
-                    row.updated_at = time.time()
-                render(
-                    windows=windows,
-                    serial=serial,
-                    index=index,
-                    sample_rate=args.sample_rate,
-                    base_mhz=args.base,
-                    roof_mhz=args.roof,
-                    step_mhz=args.step,
-                    started_at=started_at,
-                    pass_no=pass_no,
-                    current_seq=current_seq,
-                )
-            if args.passes > 0 and pass_no >= args.passes:
-                break
-    except Exception as exc:
-        print(f"scanner failed: {exc}", file=sys.stderr)
-        return 5
-    finally:
-        if probe is not None:
-            try:
-                probe.stop()
-                probe.wait()
-            except Exception:
-                pass
-
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())
-#!/usr/bin/env python3
-import argparse
-import math
-import re
-import signal
-import subprocess
-import sys
-import time
-from dataclasses import dataclass
-from typing import Dict, List, Optional, Tuple
-
-try:
-    import numpy as np
-except Exception as exc:
-    print(f"numpy import failed: {exc}", file=sys.stderr)
-    sys.exit(1)
-
-try:
-    from gnuradio import blocks, gr
-    import osmosdr
-except Exception as exc:
-    print(f"gnuradio/osmosdr import failed: {exc}", file=sys.stderr)
-    print("Run with the SDR venv, e.g. .venv-sdr/bin/python read_energy_wide.py", file=sys.stderr)
-    sys.exit(1)
-
-EPS = 1e-20
-
-
-@dataclass
-class ScanWindow:
-    seq: int
-    start_mhz: float
-    end_mhz: float
-    low_mhz: float
-    high_mhz: float
-    center_mhz: float
-    status: str = "INIT"
-    rms: Optional[float] = None
-    power_lin: Optional[float] = None
-    dbfs: Optional[float] = None
-    samples: int = 0
-    updated_at: float = 0.0
-    error: str = ""
-    pass_no: int = 0
-
-
-class WideProbeTop(gr.top_block):
-    def __init__(
-        self,
-        index: int,
-        center_freq_hz: float,
-        sample_rate: float,
-        vec_len: int,
-        gain: float,
-        if_gain: float,
-        bb_gain: float,
-    ):
-        super().__init__("hackrf_energy_wide_probe")
-        self.probe = blocks.probe_signal_vc(vec_len)
-        self.stream_to_vec = blocks.stream_to_vector(gr.sizeof_gr_complex * 1, vec_len)
-        self.src = osmosdr.source(args=f"numchan=1 hackrf={index}")
-        self.src.set_time_unknown_pps(osmosdr.time_spec_t())
-        self.src.set_sample_rate(sample_rate)
-        self.src.set_center_freq(center_freq_hz, 0)
-        try:
-            self.src.set_freq_corr(0, 0)
-        except Exception:
-            pass
-        try:
-            self.src.set_gain_mode(False, 0)
-        except Exception:
-            pass
-        for fn, val in (("set_gain", gain), ("set_if_gain", if_gain), ("set_bb_gain", bb_gain)):
-            try:
-                getattr(self.src, fn)(val, 0)
-            except Exception:
-                pass
-        try:
-            self.src.set_bandwidth(0, 0)
-        except Exception:
-            pass
-        try:
-            self.src.set_antenna("", 0)
-        except Exception:
-            pass
-        self.connect((self.src, 0), (self.stream_to_vec, 0))
-        self.connect((self.stream_to_vec, 0), (self.probe, 0))
-
-    def tune(self, freq_hz: float) -> None:
-        self.src.set_center_freq(freq_hz, 0)
-
-    def read_metrics(self) -> Tuple[float, float, float, int]:
-        arr = np.asarray(self.probe.level(), dtype=np.complex64)
-        if arr.size == 0:
-            raise RuntimeError("no samples")
-        power_lin = float(np.mean(arr.real * arr.real + arr.imag * arr.imag))
-        rms = math.sqrt(max(power_lin, 0.0))
-        dbfs = 10.0 * math.log10(max(power_lin, EPS))
-        return rms, power_lin, dbfs, int(arr.size)
-
-    def read_window(self, settle: float, avg_reads: int, pause_between_reads: float) -> Tuple[float, float, float, int]:
-        if settle > 0:
-            time.sleep(settle)
-
-        read_count = max(1, avg_reads)
-        powers: List[float] = []
-        sample_sizes: List[int] = []
-        last_error: Optional[Exception] = None
-
-        for idx in range(read_count):
-            deadline = time.time() + 1.0
-            while True:
-                try:
-                    _, power_lin, _, samples = self.read_metrics()
-                    powers.append(power_lin)
-                    sample_sizes.append(samples)
-                    break
-                except Exception as exc:
-                    last_error = exc
-                    if time.time() >= deadline:
-                        raise RuntimeError(str(last_error) if last_error else "no samples")
-                    time.sleep(0.02)
-            if idx + 1 < read_count and pause_between_reads > 0:
-                time.sleep(pause_between_reads)
-
-        power_lin = float(sum(powers) / len(powers))
-        rms = math.sqrt(max(power_lin, 0.0))
-        dbfs = 10.0 * math.log10(max(power_lin, EPS))
-        samples = int(sum(sample_sizes) / len(sample_sizes))
-        return rms, power_lin, dbfs, samples
-
-
-def parse_hackrf_info() -> Dict[str, int]:
-    try:
-        proc = subprocess.run(["hackrf_info"], capture_output=True, text=True, timeout=15)
-    except FileNotFoundError:
-        raise RuntimeError("hackrf_info not found")
-    except subprocess.TimeoutExpired:
-        raise RuntimeError("hackrf_info timeout")
-    text = (proc.stdout or "") + "\n" + (proc.stderr or "")
-    out: Dict[str, int] = {}
-    cur_idx: Optional[int] = None
-    for line in text.splitlines():
-        m = re.search(r"^Index:\s*(\d+)", line)
-        if m:
-            cur_idx = int(m.group(1))
-            continue
-        m = re.search(r"^Serial number:\s*([0-9a-fA-F]+)", line)
-        if m and cur_idx is not None:
-            out[m.group(1).lower()] = cur_idx
-    if not out:
-        raise RuntimeError("no devices parsed from hackrf_info")
-    return out
-
-
-def fmt(value: Optional[float], spec: str) -> str:
-    return "-" if value is None else format(value, spec)
-
-
-def build_windows(base_mhz: float, roof_mhz: float, step_mhz: float) -> List[ScanWindow]:
-    if step_mhz <= 0:
-        raise ValueError("step must be > 0")
-    if base_mhz == roof_mhz:
-        raise ValueError("base and roof must be different")
-
-    direction = -1.0 if roof_mhz < base_mhz else 1.0
-    edge = base_mhz
-    seq = 1
-    windows: List[ScanWindow] = []
-
-    while True:
-        next_edge = edge + direction * step_mhz
-        if direction < 0 and next_edge < roof_mhz:
-            next_edge = roof_mhz
-        if direction > 0 and next_edge > roof_mhz:
-            next_edge = roof_mhz
-
-        low_mhz = min(edge, next_edge)
-        high_mhz = max(edge, next_edge)
-        center_mhz = (low_mhz + high_mhz) / 2.0
-        windows.append(
-            ScanWindow(
-                seq=seq,
-                start_mhz=edge,
-                end_mhz=next_edge,
-                low_mhz=low_mhz,
-                high_mhz=high_mhz,
-                center_mhz=center_mhz,
-            )
-        )
-
-        if next_edge == roof_mhz:
-            break
-        edge = next_edge
-        seq += 1
-
-    return windows
-
-
-def render(
-    windows: List[ScanWindow],
-    serial: str,
-    index: int,
-    sample_rate: float,
-    base_mhz: float,
-    roof_mhz: float,
-    step_mhz: float,
-    started_at: float,
-    pass_no: int,
-    current_seq: int,
-) -> None:
-    now = time.time()
-    capture_bw_mhz = sample_rate / 1e6
-    current_row = next((row for row in windows if row.seq == current_seq), None)
-    best_row = max(
-        (row for row in windows if row.status == "OK" and row.dbfs is not None),
-        key=lambda row: row.dbfs if row.dbfs is not None else float("-inf"),
-        default=None,
-    )
-    print("\x1b[2J\x1b[H", end="")
-    print("HackRF Wide Energy Monitor (relative power: RMS / linear / dBFS)")
-    print(
-        f"serial: {serial} | idx: {index} | sample-rate: {capture_bw_mhz:.3f} MHz | "
-        f"scan: {base_mhz:.3f}->{roof_mhz:.3f} MHz step {step_mhz:.3f} MHz | "
-        f"pass: {pass_no} | uptime: {int(now-started_at)}s | {time.strftime('%Y-%m-%d %H:%M:%S')}"
-    )
-    print()
-    header = (
-        f"{'cur':>3} {'seq':>3} {'window MHz':>23} {'center':>9} {'status':>8} "
-        f"{'dBFS':>9} {'rms':>10} {'power':>12} {'N':>5} {'age':>5}  error"
-    )
-    print(header)
-    print("-" * len(header))
-    for row in windows:
-        age = "-" if row.updated_at <= 0 else f"{(now-row.updated_at):.1f}"
-        err = row.error
-        if len(err) > 50:
-            err = err[:47] + "..."
-        marker = ">>>" if row.seq == current_seq else ""
-        print(
-            f"{marker:>3} {row.seq:>3} "
-            f"{f'{row.high_mhz:.3f}-{row.low_mhz:.3f}':>23} {row.center_mhz:>9.3f} {row.status:>8} "
-            f"{fmt(row.dbfs, '.2f'):>9} {fmt(row.rms, '.6f'):>10} {fmt(row.power_lin, '.8f'):>12} "
-            f"{row.samples:>5} {age:>5}  {err}"
-        )
-    print()
-    if best_row is not None:
-        best_age = "-" if best_row.updated_at <= 0 else f"{(now-best_row.updated_at):.1f}"
-        print(
-            f"{'':>3} {'MAX':>3} "
-            f"{f'{best_row.high_mhz:.3f}-{best_row.low_mhz:.3f}':>23} {best_row.center_mhz:>9.3f} {best_row.status:>8} "
-            f"{fmt(best_row.dbfs, '.2f'):>9} {fmt(best_row.rms, '.6f'):>10} {fmt(best_row.power_lin, '.8f'):>12} "
-            f"{best_row.samples:>5} {best_age:>5}  pass={best_row.pass_no}"
-        )
-    elif current_row is not None:
-        current_age = "-" if current_row.updated_at <= 0 else f"{(now-current_row.updated_at):.1f}"
-        print(
-            f"{'':>3} {'MAX':>3} "
-            f"{f'{current_row.high_mhz:.3f}-{current_row.low_mhz:.3f}':>23} {current_row.center_mhz:>9.3f} {'INIT':>8} "
-            f"{fmt(None, '.2f'):>9} {fmt(None, '.6f'):>10} {fmt(None, '.8f'):>12} "
-            f"{0:>5} {current_age:>5}  no successful windows yet"
-        )
-    print("Ctrl+C to stop. Window width equals step; sample-rate must be >= step to cover each window.")
-    sys.stdout.flush()
-
-
-def build_parser() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(description="Retune one HackRF across a wide frequency range and measure energy")
-    parser.add_argument("--serial", required=True, help="HackRF serial number from hackrf_info")
-    parser.add_argument("--sample-rate", type=float, required=True, help="Sample rate in Hz")
-    parser.add_argument("--base", type=float, required=True, help="Scan start edge in MHz")
-    parser.add_argument("--roof", type=float, required=True, help="Scan end edge in MHz")
-    parser.add_argument("--step", type=float, required=True, help="Window width / retune step in MHz")
-    parser.add_argument("--vec-len", type=int, default=4096, help="Probe vector length")
-    parser.add_argument("--settle", type=float, default=0.12, help="Wait time after retune before reading (s)")
-    parser.add_argument("--avg-reads", type=int, default=3, help="How many probe reads to average per window")
-    parser.add_argument("--pause-between-reads", type=float, default=0.02, help="Pause between averaged reads (s)")
-    parser.add_argument("--passes", type=int, default=0, help="Number of sweep passes, 0 means infinite")
-    parser.add_argument("--gain", type=float, default=16.0, help="General gain")
-    parser.add_argument("--if-gain", type=float, default=16.0, help="IF gain")
-    parser.add_argument("--bb-gain", type=float, default=16.0, help="BB gain")
-    return parser
-
-
-def main() -> int:
-    args = build_parser().parse_args()
-    serial = args.serial.lower()
-
-    try:
-        windows = build_windows(args.base, args.roof, args.step)
-    except ValueError as exc:
-        print(f"invalid scan range: {exc}", file=sys.stderr)
-        return 2
-
-    step_hz = args.step * 1e6
-    if args.sample_rate < step_hz:
-        print(
-            f"sample-rate {args.sample_rate:.0f} Hz is smaller than step window {step_hz:.0f} Hz; "
-            "this would leave gaps in the scan",
-            file=sys.stderr,
-        )
-        return 2
-
-    try:
-        serial_to_index = parse_hackrf_info()
-    except Exception as exc:
-        print(f"hackrf discovery failed: {exc}", file=sys.stderr)
-        return 3
-
-    index = serial_to_index.get(serial)
-    if index is None:
-        print(f"serial {serial} not found in hackrf_info", file=sys.stderr)
-        print("available serials:", file=sys.stderr)
-        for item_serial, item_index in sorted(serial_to_index.items(), key=lambda item: item[1]):
-            print(f"  idx={item_index} serial={item_serial}", file=sys.stderr)
-        return 4
-
-    stop_requested = False
-
-    def on_signal(signum, frame):
-        nonlocal stop_requested
-        stop_requested = True
-
-    signal.signal(signal.SIGINT, on_signal)
-    signal.signal(signal.SIGTERM, on_signal)
-
-    probe: Optional[WideProbeTop] = None
-    started_at = time.time()
-    pass_no = 0
-    current_seq = windows[0].seq
-
-    try:
-        probe = WideProbeTop(
-            index=index,
-            center_freq_hz=windows[0].center_mhz * 1e6,
-            sample_rate=args.sample_rate,
-            vec_len=args.vec_len,
-            gain=args.gain,
-            if_gain=args.if_gain,
-            bb_gain=args.bb_gain,
-        )
-        probe.start()
-        time.sleep(max(args.settle, 0.12))
-
-        while not stop_requested:
-            pass_no += 1
-            for row in windows:
-                if stop_requested:
-                    break
-                current_seq = row.seq
-                try:
-                    probe.tune(row.center_mhz * 1e6)
-                    rms, power_lin, dbfs, samples = probe.read_window(
-                        settle=args.settle,
-                        avg_reads=args.avg_reads,
-                        pause_between_reads=args.pause_between_reads,
-                    )
-                    row.status = "OK"
-                    row.rms = rms
-                    row.power_lin = power_lin
-                    row.dbfs = dbfs
-                    row.samples = samples
-                    row.error = ""
-                    row.updated_at = time.time()
-                    row.pass_no = pass_no
-                except Exception as exc:
-                    row.status = "ERR"
-                    row.error = str(exc)
-                    row.updated_at = time.time()
-                render(
-                    windows=windows,
-                    serial=serial,
-                    index=index,
-                    sample_rate=args.sample_rate,
-                    base_mhz=args.base,
-                    roof_mhz=args.roof,
-                    step_mhz=args.step,
-                    started_at=started_at,
-                    pass_no=pass_no,
-                    current_seq=current_seq,
-                )
-            if args.passes > 0 and pass_no >= args.passes:
-                break
-    except Exception as exc:
-        print(f"scanner failed: {exc}", file=sys.stderr)
-        return 5
-    finally:
-        if probe is not None:
-            try:
-                probe.stop()
-                probe.wait()
-            except Exception:
-                pass
-
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

restart_all.sh

@@ -7,6 +7,8 @@ COMPOSE_FILE="${PROJECT_ROOT}/deploy/docker/docker-compose.yml"
 SDR_UNITS=(
   dronedetector-sdr-433.service
   dronedetector-sdr-750.service
+  #dronedetector-sdr-868-915.service
+  dronedetector-sdr-868.service
   dronedetector-sdr-1500.service
   dronedetector-sdr-3300.service
   dronedetector-sdr-4500.service
@@ -17,51 +19,10 @@ SDR_UNITS=(
   dronedetector-sdr-2400.service
 )
 
-CONFIGURED_SDR_UNITS=()
-
 log() {
   printf '[restart_all] %s\n' "$*"
 }
 
-sdr_unit_env_key() {
-  local unit="$1"
-  local band="${unit#dronedetector-sdr-}"
-  band="${band%.service}"
-  printf 'hack_%s\n' "$band"
-}
-
-get_env_value() {
-  local key="$1"
-  awk -F= -v key="$key" '
-    $1 == key {
-      value = substr($0, index($0, "=") + 1)
-      sub(/^[[:space:]]+/, "", value)
-      sub(/[[:space:]]+$/, "", value)
-      gsub(/^"/, "", value)
-      gsub(/"$/, "", value)
-      gsub(/^'\''/, "", value)
-      gsub(/'\''$/, "", value)
-      print value
-      exit
-    }
-  ' "${PROJECT_ROOT}/.env"
-}
-
-populate_configured_sdr_units() {
-  CONFIGURED_SDR_UNITS=()
-
-  local unit env_key env_value
-  for unit in "${SDR_UNITS[@]}"; do
-    env_key="$(sdr_unit_env_key "$unit")"
-    env_value="$(get_env_value "$env_key")"
-    if [[ -n "$env_value" ]]; then
-      CONFIGURED_SDR_UNITS+=("$unit")
-    else
-      log "Skipping ${unit}: ${env_key} is empty in .env"
-    fi
-  done
-}
-
 if [[ -x /usr/bin/sudo ]]; then
   SUDO=(sudo)
 else
@@ -80,7 +41,7 @@ restart_docker_services() {
 
 restart_sdr_services() {
   log "Restarting SDR systemd units"
-  for unit in "${CONFIGURED_SDR_UNITS[@]}"; do
+  for unit in "${SDR_UNITS[@]}"; do
     ${SUDO[@]} systemctl restart "$unit"
   done
 }
@@ -90,7 +51,7 @@ print_status() {
   docker compose -f "$COMPOSE_FILE" ps || true
 
   log "SDR status"
-  for unit in "${CONFIGURED_SDR_UNITS[@]}"; do
+  for unit in "${SDR_UNITS[@]}"; do
     if ${SUDO[@]} systemctl is-active --quiet "$unit"; then
       printf '%s: active\n' "$unit"
     else
@@ -100,7 +61,6 @@ print_status() {
 }
 
 main() {
-  populate_configured_sdr_units
   restart_docker_services
   restart_sdr_services
   print_status

scripts/capture_nn_results.py

@@ -0,0 +1,223 @@
+#!/usr/bin/env python3
+import argparse
+import csv
+import json
+import os
+import re
+import subprocess
+import sys
+import time
+from datetime import datetime, timezone
+
+
+RESULT_RE = re.compile(
+    r"^(?P<docker_ts>\S+)\s+RESULT Модель (?P<model_id>\d+) с типом (?P<model_type>.+?): "
+    r"(?P<prediction>\S+) \(probability=(?P<probability>[-+]?\d+(?:\.\d+)?)\)\s*$"
+)
+FREQ_RE = re.compile(r"(\d{3,5})")
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description="Capture NN inference RESULT logs into CSV or JSONL until time or size limit."
+    )
+    parser.add_argument(
+        "--output",
+        required=True,
+        help="Output file path (.csv or .jsonl recommended).",
+    )
+    parser.add_argument(
+        "--format",
+        choices=("csv", "jsonl"),
+        default="csv",
+        help="Output format.",
+    )
+    parser.add_argument(
+        "--minutes",
+        type=float,
+        default=0.0,
+        help="Stop after this many minutes. 0 means no time limit.",
+    )
+    parser.add_argument(
+        "--max-bytes",
+        type=int,
+        default=3 * 1024 * 1024 * 1024,
+        help="Stop when output file reaches this size in bytes. Default: 3 GiB.",
+    )
+    parser.add_argument(
+        "--since",
+        default=None,
+        help="Optional docker logs --since value, e.g. 20m, 2h, 2026-05-04T12:00:00.",
+    )
+    parser.add_argument(
+        "--tail",
+        type=int,
+        default=0,
+        help="How many previous log lines to include before following. Default: 0.",
+    )
+    parser.add_argument(
+        "--compose-file",
+        default="deploy/docker/docker-compose.yml",
+        help="Path to docker compose file.",
+    )
+    parser.add_argument(
+        "--service",
+        default="dronedetector-nn-server",
+        help="Docker compose service name.",
+    )
+    parser.add_argument(
+        "--follow",
+        action="store_true",
+        help="Follow logs live. By default the script captures a finite history snapshot.",
+    )
+    return parser.parse_args()
+
+
+def extract_freq(model_type):
+    matches = FREQ_RE.findall(model_type)
+    if not matches:
+        return ""
+    known_freqs = {"433", "750", "868", "915", "1200", "1500", "2400", "3300", "4500", "5200", "5800"}
+    for value in matches:
+        if value in known_freqs:
+            return value
+    return matches[0]
+
+
+def parse_docker_timestamp(value):
+    try:
+        return datetime.fromisoformat(value.replace("Z", "+00:00"))
+    except ValueError:
+        return datetime.now(timezone.utc)
+
+
+def open_output(path, fmt):
+    os.makedirs(os.path.dirname(os.path.abspath(path)), exist_ok=True)
+    fh = open(path, "a", encoding="utf-8", newline="")
+    writer = None
+    if fmt == "csv":
+        writer = csv.writer(fh)
+        if fh.tell() == 0:
+            writer.writerow(
+                [
+                    "docker_timestamp",
+                    "event_time_iso",
+                    "event_time_epoch",
+                    "freq",
+                    "model_id",
+                    "model_type",
+                    "prediction",
+                    "probability",
+                ]
+            )
+            fh.flush()
+    return fh, writer
+
+
+def write_record(fh, writer, fmt, record):
+    if fmt == "csv":
+        writer.writerow(
+            [
+                record["docker_timestamp"],
+                record["event_time_iso"],
+                record["event_time_epoch"],
+                record["freq"],
+                record["model_id"],
+                record["model_type"],
+                record["prediction"],
+                record["probability"],
+            ]
+        )
+    else:
+        fh.write(json.dumps(record, ensure_ascii=False) + "\n")
+    fh.flush()
+
+
+def build_command(args):
+    cmd = [
+        "docker",
+        "compose",
+        "-f",
+        args.compose_file,
+        "logs",
+        "--timestamps",
+        "--no-log-prefix",
+        args.service,
+    ]
+    if args.since:
+        cmd[5:5] = ["--since", args.since]
+    if int(args.tail) > 0:
+        cmd[-1:-1] = ["--tail", str(args.tail)]
+    if args.follow:
+        cmd.insert(-1, "-f")
+    return cmd
+
+
+def main():
+    args = parse_args()
+    deadline = time.time() + (args.minutes * 60.0) if args.minutes > 0 else None
+
+    fh, writer = open_output(args.output, args.format)
+    cmd = build_command(args)
+
+    print("Running:", " ".join(cmd), file=sys.stderr)
+    proc = subprocess.Popen(
+        cmd,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+        encoding="utf-8",
+        errors="replace",
+        bufsize=1,
+    )
+
+    captured = 0
+    try:
+        assert proc.stdout is not None
+        for line in proc.stdout:
+            if deadline is not None and time.time() >= deadline:
+                print("Stopping: time limit reached", file=sys.stderr)
+                break
+
+            match = RESULT_RE.match(line.rstrip("\n"))
+            if not match:
+                continue
+
+            docker_dt = parse_docker_timestamp(match.group("docker_ts"))
+            event_dt = docker_dt.astimezone()
+            model_type = match.group("model_type")
+            record = {
+                "docker_timestamp": match.group("docker_ts"),
+                "event_time_iso": event_dt.isoformat(timespec="seconds"),
+                "event_time_epoch": round(docker_dt.timestamp(), 3),
+                "freq": extract_freq(model_type),
+                "model_id": int(match.group("model_id")),
+                "model_type": model_type,
+                "prediction": match.group("prediction"),
+                "probability": float(match.group("probability")),
+            }
+            write_record(fh, writer, args.format, record)
+            captured += 1
+
+            if fh.tell() >= args.max_bytes:
+                print("Stopping: file size limit reached", file=sys.stderr)
+                break
+    finally:
+        try:
+            proc.terminate()
+        except Exception:
+            pass
+        try:
+            proc.wait(timeout=5)
+        except Exception:
+            try:
+                proc.kill()
+            except Exception:
+                pass
+        fh.close()
+
+    print(f"Captured {captured} inference results into {args.output}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

src/main_1200.py

@@ -40,8 +40,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(self.samp_rate)
         self.rtlsdr_source_0.set_center_freq(self.center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(24, 0)
+        self.rtlsdr_source_0.set_if_gain(24, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_1500.py

@@ -40,8 +40,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(self.samp_rate)
         self.rtlsdr_source_0.set_center_freq(self.center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(24, 0)
+        self.rtlsdr_source_0.set_if_gain(24, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_2400.py

@@ -40,8 +40,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(self.samp_rate)
         self.rtlsdr_source_0.set_center_freq(self.center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(0, 0)
+        self.rtlsdr_source_0.set_if_gain(0, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_3300.py

@@ -94,8 +94,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(samp_rate)
         self.rtlsdr_source_0.set_center_freq(center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(100, 0)
+        self.rtlsdr_source_0.set_if_gain(100, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_433.py

@@ -94,8 +94,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(samp_rate)
         self.rtlsdr_source_0.set_center_freq(center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(24, 0)
+        self.rtlsdr_source_0.set_if_gain(24, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_4500.py

@@ -94,8 +94,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(samp_rate)
         self.rtlsdr_source_0.set_center_freq(center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(100, 0)
+        self.rtlsdr_source_0.set_if_gain(100, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_5200.py

@@ -93,8 +93,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(samp_rate)
         self.rtlsdr_source_0.set_center_freq(center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(100, 0)
+        self.rtlsdr_source_0.set_if_gain(100, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_5800.py

@@ -94,8 +94,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(samp_rate)
         self.rtlsdr_source_0.set_center_freq(center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(100, 0)
+        self.rtlsdr_source_0.set_if_gain(100, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_750.py

@@ -94,8 +94,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(samp_rate)
         self.rtlsdr_source_0.set_center_freq(center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(24, 0)
+        self.rtlsdr_source_0.set_if_gain(24, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/main_868.py

@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+from gnuradio import blocks
+from gnuradio import gr
+from gnuradio import zeromq
+import signal
+import sys
+import threading
+import time
+
+import embedded_868 as my_freq
+
+from common.runtime import load_root_env
+from common.shared_stream_addrs import SHARED_868_ADDR, SHARED_VECTOR_LEN
+
+
+load_root_env(__file__)
+
+
+class get_center_freq(gr.top_block):
+    def __init__(self):
+        gr.top_block.__init__(self, 'get_center_freq')
+
+        self.prob_freq = 0
+        self.poll_rate = 10000
+        self.vector_len = SHARED_VECTOR_LEN
+        self.center_freq = 0
+        self.shared_addr = SHARED_868_ADDR
+        self._stop_polling = threading.Event()
+        self._prob_freq_thread = None
+
+        self.probSigVec = blocks.probe_signal_vc(self.vector_len)
+        self.shared_source_0 = zeromq.pull_source(
+            gr.sizeof_gr_complex,
+            self.vector_len,
+            self.shared_addr,
+            100,
+            False,
+            -1,
+            False,
+        )
+        self.connect((self.shared_source_0, 0), (self.probSigVec, 0))
+
+    def start_polling(self):
+        if self._prob_freq_thread is not None:
+            return
+
+        def _prob_freq_probe():
+            while not self._stop_polling.is_set():
+                self.set_prob_freq(self.probSigVec.level())
+                time.sleep(1.0 / self.poll_rate)
+
+        self._prob_freq_thread = threading.Thread(target=_prob_freq_probe, daemon=True)
+        self._prob_freq_thread.start()
+
+    def get_prob_freq(self):
+        return self.prob_freq
+
+    def set_prob_freq(self, prob_freq):
+        self.prob_freq = prob_freq
+        self.center_freq = my_freq.work(self.prob_freq)
+
+    def get_center_freq(self):
+        return self.center_freq
+
+    def set_center_freq(self, center_freq):
+        self.center_freq = center_freq
+
+    def close(self):
+        self._stop_polling.set()
+        self.stop()
+        self.wait()
+
+
+def main(top_block_cls=get_center_freq, options=None):
+    tb = top_block_cls()
+
+    def sig_handler(sig=None, frame=None):
+        tb.close()
+        sys.exit(0)
+
+    signal.signal(signal.SIGINT, sig_handler)
+    signal.signal(signal.SIGTERM, sig_handler)
+
+    tb.start()
+    tb.start_polling()
+    try:
+        print('shared_pull_addr:', SHARED_868_ADDR)
+        print('debug_flag:', my_freq.debug_flag)
+        print('save_data_flag:', my_freq.save_data_flag)
+        print('send_to_module_flag:', my_freq.send_to_module_flag)
+    except EOFError:
+        pass
+    tb.wait()
+
+
+if __name__ == '__main__':
+    main()

src/main_868_915_router.py

@@ -0,0 +1,122 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+from gnuradio import blocks
+from gnuradio import gr
+import signal
+import sys
+import threading
+import time
+
+import osmosdr
+
+from common.runtime import load_root_env, resolve_hackrf_index
+from common.shared_stream_addrs import SHARED_VECTOR_LEN
+from shared_router_868_915 import SharedRouter868915
+
+
+load_root_env(__file__)
+
+
+def get_hack_id():
+    return resolve_hackrf_index('hack_868', 'src/main_868_915_router.py')
+
+
+class get_center_freq(gr.top_block):
+    def __init__(self):
+        gr.top_block.__init__(self, 'get_center_freq')
+
+        self.prob_freq = 0
+        self.poll_rate = 10000
+        self.vector_len = SHARED_VECTOR_LEN
+        self.router = SharedRouter868915()
+        self.active_lane = self.router.get_active_name()
+        self.center_freq = self.router.get_start_freq()
+        self._stop_polling = threading.Event()
+        self._prob_freq_thread = None
+
+        self.probSigVec = blocks.probe_signal_vc(self.vector_len)
+        self.rtlsdr_source_0 = osmosdr.source(
+            args='numchan=' + str(1) + ' ' + 'hackrf=' + get_hack_id()
+        )
+        self.rtlsdr_source_0.set_time_unknown_pps(osmosdr.time_spec_t())
+        self.rtlsdr_source_0.set_freq_corr(0, 0)
+        self.rtlsdr_source_0.set_antenna('', 0)
+        self.rtlsdr_source_0.set_min_output_buffer(self.vector_len)
+        self.apply_active_frontend()
+        self.rtlsdr_source_0.set_center_freq(self.center_freq, 0)
+
+        self.blocks_stream_to_vector_1 = blocks.stream_to_vector(gr.sizeof_gr_complex * 1, self.vector_len)
+        self.connect((self.rtlsdr_source_0, 0), (self.blocks_stream_to_vector_1, 0))
+        self.connect((self.blocks_stream_to_vector_1, 0), (self.probSigVec, 0))
+
+    def start_polling(self):
+        if self._prob_freq_thread is not None:
+            return
+
+        def _prob_freq_probe():
+            while not self._stop_polling.is_set():
+                self.set_prob_freq(self.probSigVec.level())
+                time.sleep(1.0 / self.poll_rate)
+
+        self._prob_freq_thread = threading.Thread(target=_prob_freq_probe, daemon=True)
+        self._prob_freq_thread.start()
+
+    def apply_active_frontend(self):
+        frontend = self.router.get_active_frontend()
+        self.rtlsdr_source_0.set_sample_rate(frontend['sample_rate'])
+        self.rtlsdr_source_0.set_gain(frontend['gain'], 0)
+        self.rtlsdr_source_0.set_if_gain(frontend['if_gain'], 0)
+        self.rtlsdr_source_0.set_bb_gain(frontend['bb_gain'], 0)
+        self.rtlsdr_source_0.set_bandwidth(frontend['bandwidth'], 0)
+
+    def get_prob_freq(self):
+        return self.prob_freq
+
+    def set_prob_freq(self, prob_freq):
+        self.prob_freq = prob_freq
+        next_center, lane_switched = self.router.route_vector(self.prob_freq)
+        if lane_switched:
+            self.active_lane = self.router.get_active_name()
+            self.apply_active_frontend()
+        if next_center != self.center_freq:
+            self.set_center_freq(next_center)
+
+    def get_center_freq(self):
+        return self.center_freq
+
+    def set_center_freq(self, center_freq):
+        self.center_freq = center_freq
+        self.rtlsdr_source_0.set_center_freq(self.center_freq, 0)
+
+    def close(self):
+        self._stop_polling.set()
+        try:
+            self.router.close()
+        finally:
+            self.stop()
+            self.wait()
+
+
+def main(top_block_cls=get_center_freq, options=None):
+    tb = top_block_cls()
+
+    def sig_handler(sig=None, frame=None):
+        tb.close()
+        sys.exit(0)
+
+    signal.signal(signal.SIGINT, sig_handler)
+    signal.signal(signal.SIGTERM, sig_handler)
+
+    tb.start()
+    tb.start_polling()
+    try:
+        print('shared_router_active_lane:', tb.router.get_active_name())
+        print('shared_router_start_freq:', tb.get_center_freq())
+    except EOFError:
+        pass
+    tb.wait()
+
+
+if __name__ == '__main__':
+    main()

src/main_915.py

@@ -40,8 +40,8 @@ class get_center_freq(gr.top_block):
         self.rtlsdr_source_0.set_sample_rate(self.samp_rate)
         self.rtlsdr_source_0.set_center_freq(self.center_freq, 0)
         self.rtlsdr_source_0.set_freq_corr(0, 0)
-        self.rtlsdr_source_0.set_gain(16, 0)
-        self.rtlsdr_source_0.set_if_gain(16, 0)
+        self.rtlsdr_source_0.set_gain(24, 0)
+        self.rtlsdr_source_0.set_if_gain(24, 0)
         self.rtlsdr_source_0.set_bb_gain(100, 0)
         self.rtlsdr_source_0.set_antenna('', 0)
         self.rtlsdr_source_0.set_bandwidth(0, 0)

src/server_to_master.py

@@ -298,7 +298,7 @@ async def agregate_data(data_to_agregate: list):
 
     data = []
 
-    if any(item is not None for item in data_to_agregate):
+    if all(item is not None for item in data_to_agregate):
         for item in data_to_agregate:
             if item is not None:
                 item['freq'] = int(item['freq'])

src/shared_router_868_915.py

@@ -0,0 +1,173 @@
+import os
+
+import numpy as np
+import zmq
+
+from common.runtime import load_root_env
+from common.shared_stream_addrs import SHARED_868_ADDR, SHARED_915_ADDR
+from core.multichannelswitcher import MultiChannel
+from core.sig_n_medi_collect import Signal
+
+
+load_root_env(__file__)
+
+
+class Scheduler868:
+    def __init__(self):
+        self.signal_length = int(os.getenv('signal_length_868'))
+        self.multi_channel = MultiChannel(
+            [*map(float, os.getenv('f_step_868').split())],
+            [*map(float, os.getenv('f_bases_868').split())],
+            [*map(float, os.getenv('f_roofs_868').split())],
+        )
+        self.base_freq = float(self.multi_channel.init_f())
+        self.signal = Signal()
+
+    def get_current_freq(self):
+        return float(self.multi_channel.get_cur_channel())
+
+    def process(self, lvl):
+        current_before = self.get_current_freq()
+        metric = self.signal.fill_signal(lvl, self.signal_length)
+        if metric == 0:
+            return current_before, False
+
+        next_freq = float(self.multi_channel.change_channel())
+        self.signal.clear()
+        lane_complete = next_freq == self.base_freq and current_before != self.base_freq
+        return next_freq, lane_complete
+
+
+class Scheduler915:
+    def __init__(self):
+        self.porog = float(os.getenv('POROG_915'))
+        self.point_amount = 100_000
+        self.split_size = 400_000
+        self.show_amount = int(0.8 * self.point_amount)
+        self.f_base = 0.91e9
+        self.f_step = 20e6
+        self.f_roof = 0.98e9
+        self.f = self.f_base
+        self.channel = 1
+        self.flag = 0
+        self.signal_arr = np.array([], dtype=np.complex64)
+
+    def get_current_freq(self):
+        return float(self.f)
+
+    def _median(self, sig):
+        samples = np.asarray(np.abs(np.array(sig, dtype=np.complex64)), dtype=np.float32)
+        sorted_samples = sorted(samples)
+        median = abs(float(np.median(sorted_samples[self.show_amount:])))
+        self.flag = 0 if self.porog > median else 1
+
+    def _advance(self):
+        next_freq = self.f + self.f_step
+        if next_freq >= self.f_roof:
+            self.f = self.f_base
+            self.channel = 1
+            return float(self.f), True
+
+        self.f = next_freq
+        self.channel += 1
+        return float(self.f), False
+
+    def process(self, lvl):
+        y = np.asarray(lvl, dtype=np.complex64).ravel()
+        self.signal_arr = np.concatenate((self.signal_arr, y), axis=None)
+
+        if self.flag == 0 and len(self.signal_arr) >= self.point_amount:
+            self._median(self.signal_arr[:self.point_amount])
+            self.signal_arr = np.array([], dtype=np.complex64)
+            if self.flag == 0:
+                return self._advance()
+
+        if len(self.signal_arr) >= self.split_size:
+            self.flag = 0
+            self.signal_arr = np.array([], dtype=np.complex64)
+            return self._advance()
+
+        return float(self.f), False
+
+
+class SharedRouter868915:
+    def __init__(self):
+        self.frontends = {
+            '868': {
+                'sample_rate': 20e6,
+                'gain': 24,
+                'if_gain': 24,
+                'bb_gain': 100,
+                'bandwidth': 0,
+            },
+            '915': {
+                'sample_rate': 20e6,
+                'gain': 16,
+                'if_gain': 16,
+                'bb_gain': 0,
+                'bandwidth': 0,
+            },
+        }
+        self.schedulers = {
+            '868': Scheduler868(),
+            '915': Scheduler915(),
+        }
+        self.context = zmq.Context.instance()
+        self.sockets = {
+            '868': self._make_socket(SHARED_868_ADDR),
+            '915': self._make_socket(SHARED_915_ADDR),
+        }
+        self.active_name = '868'
+        self.switch_counter = 0
+
+    def _make_socket(self, addr):
+        sock = self.context.socket(zmq.PUSH)
+        sock.setsockopt(zmq.SNDHWM, 64)
+        sock.setsockopt(zmq.LINGER, 0)
+        sock.setsockopt(zmq.IMMEDIATE, 1)
+        sock.bind(addr)
+        return sock
+
+    def close(self):
+        for sock in self.sockets.values():
+            try:
+                sock.close(0)
+            except Exception:
+                pass
+
+    def get_active_name(self):
+        return self.active_name
+
+    def get_active_freq(self):
+        return self.schedulers[self.active_name].get_current_freq()
+
+    def get_active_frontend(self):
+        return dict(self.frontends[self.active_name])
+
+    def get_start_freq(self):
+        return self.get_active_freq()
+
+    def route_vector(self, lvl):
+        vector = np.asarray(lvl, dtype=np.complex64).ravel()
+        active_name = self.active_name
+
+        try:
+            self.sockets[active_name].send(vector.tobytes(), zmq.NOBLOCK)
+        except zmq.Again:
+            pass
+
+        next_freq, lane_complete = self.schedulers[active_name].process(vector)
+        lane_switched = False
+
+        if lane_complete:
+            previous = self.active_name
+            self.active_name = '915' if self.active_name == '868' else '868'
+            next_freq = self.get_active_freq()
+            self.switch_counter += 1
+            lane_switched = True
+            print(
+                f'[shared-router-868-915] switch#{self.switch_counter}: '
+                f'{previous} -> {self.active_name}, tune={next_freq}'
+            )
+
+        return float(next_freq), lane_switched

telemetry/telemetry_server.py

@@ -1,11 +1,13 @@
 import asyncio
 import os
+import re
 import time
 from collections import defaultdict, deque
+from pathlib import Path
 from typing import Any, Deque, Dict, List, Optional
 
-from fastapi import FastAPI, Query, WebSocket, WebSocketDisconnect
-from fastapi.responses import HTMLResponse
+from fastapi import FastAPI, HTTPException, Query, WebSocket, WebSocketDisconnect
+from fastapi.responses import FileResponse, HTMLResponse
 from pydantic import BaseModel, Field
 
 from common.runtime import load_root_env
@@ -16,15 +18,25 @@ TELEMETRY_BIND_HOST = os.getenv('telemetry_bind_host', os.getenv('lochost', '0.0
 TELEMETRY_BIND_PORT = int(os.getenv('telemetry_bind_port', os.getenv('telemetry_port', '5020')))
 TELEMETRY_HISTORY_SEC = int(float(os.getenv('telemetry_history_sec', '900')))
 TELEMETRY_MAX_POINTS_PER_FREQ = int(os.getenv('telemetry_max_points_per_freq', '5000'))
+INFERENCE_HISTORY_SEC = int(float(os.getenv('inference_history_sec', str(TELEMETRY_HISTORY_SEC))))
+INFERENCE_MAX_RESULTS_PER_FREQ = int(os.getenv('inference_max_results_per_freq', '100'))
+INFERENCE_RESULT_DIR = Path(os.getenv('inference_result_dir', '/app/inference_result')).resolve()
+INFERENCE_IMAGE_RE = re.compile(r"_inference_(\d+)_")
 
 
 def _new_buffer() -> Deque[Dict[str, Any]]:
     return deque(maxlen=TELEMETRY_MAX_POINTS_PER_FREQ)
 
 
+def _new_inference_buffer() -> Deque[Dict[str, Any]]:
+    return deque(maxlen=INFERENCE_MAX_RESULTS_PER_FREQ)
+
+
 app = FastAPI(title='DroneDetector Telemetry Server')
 _buffers: Dict[str, Deque[Dict[str, Any]]] = defaultdict(_new_buffer)
 _ws_clients: List[WebSocket] = []
+_inference_buffers: Dict[str, Deque[Dict[str, Any]]] = defaultdict(_new_inference_buffer)
+_inference_ws_clients: List[WebSocket] = []
 _state_lock = asyncio.Lock()
 
 
@@ -41,6 +53,18 @@ class TelemetryPoint(BaseModel):
     alarm_channels: Optional[List[int]] = None
 
 
+class InferenceResult(BaseModel):
+    result_id: int
+    ts: float = Field(default_factory=lambda: time.time())
+    freq: str
+    model: str
+    prediction: str
+    probability: float
+    drone_probability: Optional[float] = None
+    drone_threshold: Optional[str] = None
+    images: List[str] = Field(default_factory=list)
+
+
 def _prune_freq_locked(freq: str, now_ts: float) -> None:
     cutoff = now_ts - TELEMETRY_HISTORY_SEC
     buf = _buffers[freq]
@@ -62,6 +86,71 @@ def _copy_series_locked(seconds: int, freq: Optional[str] = None) -> Dict[str, L
     return series
 
 
+def _prune_inference_freq_locked(freq: str, now_ts: float) -> None:
+    cutoff = now_ts - INFERENCE_HISTORY_SEC
+    buf = _inference_buffers[freq]
+    while buf and float(buf[0].get('ts', 0.0)) < cutoff:
+        buf.popleft()
+
+
+def _copy_inference_series_locked(limit: int, freq: Optional[str] = None) -> Dict[str, List[Dict[str, Any]]]:
+    now_ts = time.time()
+    cutoff = now_ts - INFERENCE_HISTORY_SEC
+
+    def _slice(buf: Deque[Dict[str, Any]]) -> List[Dict[str, Any]]:
+        recent = [item for item in buf if float(item.get('ts', 0.0)) >= cutoff]
+        return recent[-limit:]
+
+    if freq is not None:
+        return {freq: _slice(_inference_buffers.get(freq, deque()))}
+
+    series: Dict[str, List[Dict[str, Any]]] = {}
+    for key, buf in _inference_buffers.items():
+        series[key] = _slice(buf)
+    return series
+
+
+def _sanitize_image_names(names: List[str]) -> List[str]:
+    safe_names: List[str] = []
+    for name in names:
+        base = Path(str(name)).name
+        if not base or not base.endswith('.png'):
+            continue
+        safe_names.append(base)
+    return safe_names
+
+
+def _resolve_latest_images_for_model(payload: Dict[str, Any]) -> Dict[str, Any]:
+    model_name = str(payload.get('model', ''))
+    if not model_name or not INFERENCE_RESULT_DIR.is_dir():
+        payload['images'] = _sanitize_image_names(payload.get('images', []))
+        return payload
+
+    model_suffix = f"_{model_name}.png"
+    grouped: Dict[int, List[str]] = {}
+    for path in INFERENCE_RESULT_DIR.iterdir():
+        if not path.is_file():
+            continue
+        name = path.name
+        if not name.endswith(model_suffix):
+            continue
+        match = INFERENCE_IMAGE_RE.search(name)
+        if match is None:
+            continue
+        grouped.setdefault(int(match.group(1)), []).append(name)
+
+    if not grouped:
+        payload['images'] = _sanitize_image_names(payload.get('images', []))
+        return payload
+
+    current_id = int(payload.get('result_id', 0) or 0)
+    if current_id in grouped:
+        payload['images'] = sorted(grouped[current_id])
+    else:
+        payload['images'] = _sanitize_image_names(payload.get('images', []))
+    return payload
+
+
 async def _broadcast(message: Dict[str, Any]) -> None:
     dead: List[WebSocket] = []
     for ws in list(_ws_clients):
@@ -77,6 +166,21 @@ async def _broadcast(message: Dict[str, Any]) -> None:
                     _ws_clients.remove(ws)
 
 
+async def _broadcast_inference(message: Dict[str, Any]) -> None:
+    dead: List[WebSocket] = []
+    for ws in list(_inference_ws_clients):
+        try:
+            await ws.send_json(message)
+        except Exception:
+            dead.append(ws)
+
+    if dead:
+        async with _state_lock:
+            for ws in dead:
+                if ws in _inference_ws_clients:
+                    _inference_ws_clients.remove(ws)
+
+
 @app.post('/telemetry')
 async def ingest_telemetry(point: TelemetryPoint):
     payload = point.model_dump()
@@ -102,6 +206,31 @@ async def telemetry_history(
     return {'seconds': seconds, 'series': series}
 
 
+@app.post('/inference/result')
+async def ingest_inference_result(result: InferenceResult):
+    payload = result.model_dump()
+    payload = _resolve_latest_images_for_model(payload)
+    freq = str(payload['freq'])
+    now_ts = time.time()
+
+    async with _state_lock:
+        _inference_buffers[freq].append(payload)
+        _prune_inference_freq_locked(freq, now_ts)
+
+    await _broadcast_inference({'type': 'inference_result', 'data': payload})
+    return {'ok': True}
+
+
+@app.get('/inference/history')
+async def inference_history(
+    freq: Optional[str] = Query(default=None),
+    limit: int = Query(default=20, ge=1, le=200),
+):
+    async with _state_lock:
+        series = _copy_inference_series_locked(limit=limit, freq=freq)
+    return {'limit': limit, 'series': series}
+
+
 @app.websocket('/telemetry/ws')
 async def telemetry_ws(websocket: WebSocket):
     await websocket.accept()
@@ -123,6 +252,26 @@ async def telemetry_ws(websocket: WebSocket):
                 _ws_clients.remove(websocket)
 
 
+@app.websocket('/inference/ws')
+async def inference_ws(websocket: WebSocket):
+    await websocket.accept()
+    async with _state_lock:
+        _inference_ws_clients.append(websocket)
+        snapshot = _copy_inference_series_locked(limit=20, freq=None)
+
+    await websocket.send_json({'type': 'snapshot', 'data': snapshot})
+
+    try:
+        while True:
+            await websocket.receive_text()
+    except WebSocketDisconnect:
+        pass
+    finally:
+        async with _state_lock:
+            if websocket in _inference_ws_clients:
+                _inference_ws_clients.remove(websocket)
+
+
 MONITOR_HTML = """
 <!doctype html>
 <html>
@@ -453,12 +602,294 @@ loadInitial().then(connectWs).catch((e) => {
 """
 
 
+INFERENCE_VIEWER_HTML = """
+<!doctype html>
+<html>
+<head>
+  <meta charset="utf-8" />
+  <meta name="viewport" content="width=device-width, initial-scale=1" />
+  <title>DroneDetector Inference Viewer</title>
+  <style>
+    :root {
+      --bg: #f4f6f8;
+      --card: #ffffff;
+      --line: #d7dde5;
+      --text: #1c232e;
+      --muted: #647084;
+      --ok: #16a34a;
+      --warn: #b45309;
+      --accent: #0f6fff;
+    }
+    * { box-sizing: border-box; }
+    body { margin: 0; background: var(--bg); color: var(--text); font-family: system-ui, -apple-system, Segoe UI, sans-serif; }
+    .wrap { max-width: 1800px; margin: 0 auto; padding: 16px; }
+    .head { display: flex; justify-content: space-between; align-items: center; gap: 16px; margin-bottom: 16px; }
+    .meta { color: var(--muted); font-size: 13px; }
+    .actions { display: flex; gap: 8px; align-items: center; }
+    button { border: 1px solid var(--line); background: var(--card); color: var(--text); border-radius: 8px; padding: 8px 12px; cursor: pointer; }
+    button.primary { background: var(--accent); color: #fff; border-color: var(--accent); }
+    .grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(520px, 1fr)); gap: 14px; }
+    .card { background: var(--card); border: 1px solid var(--line); border-radius: 14px; padding: 14px; }
+    .card-head { display: flex; justify-content: space-between; align-items: start; gap: 12px; margin-bottom: 10px; }
+    .freq { font-size: 28px; font-weight: 700; }
+    .pill { display: inline-flex; align-items: center; gap: 6px; border-radius: 999px; padding: 4px 10px; font-size: 12px; }
+    .pill.live { background: #dcfce7; color: #166534; }
+    .pill.paused { background: #fef3c7; color: #92400e; }
+    .summary { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 8px 12px; margin-bottom: 12px; }
+    .summary-item { border: 1px solid var(--line); border-radius: 10px; padding: 8px 10px; }
+    .summary-label { color: var(--muted); font-size: 12px; margin-bottom: 4px; }
+    .summary-value { font-size: 14px; font-weight: 600; word-break: break-word; }
+    .images { display: grid; grid-template-columns: repeat(auto-fit, minmax(150px, 1fr)); gap: 10px; margin-bottom: 12px; }
+    .image-card { border: 1px solid var(--line); border-radius: 10px; overflow: hidden; background: #f8fafc; }
+    .image-card img { width: 100%; height: 180px; object-fit: contain; display: block; background: #fff; }
+    .image-card .cap { padding: 6px 8px; font-size: 12px; color: var(--muted); border-top: 1px solid var(--line); }
+    .history-title { font-size: 13px; font-weight: 600; margin-bottom: 8px; }
+    .history { display: flex; gap: 8px; overflow-x: auto; padding-bottom: 4px; }
+    .thumb { min-width: 110px; max-width: 110px; border: 1px solid var(--line); border-radius: 10px; background: #fff; padding: 6px; cursor: pointer; }
+    .thumb.active { border-color: var(--accent); box-shadow: inset 0 0 0 1px var(--accent); }
+    .thumb img { width: 100%; height: 70px; object-fit: contain; display: block; background: #f8fafc; border-radius: 6px; }
+    .thumb .t1 { font-size: 12px; font-weight: 600; margin-top: 6px; }
+    .thumb .t2 { font-size: 11px; color: var(--muted); }
+    .empty { color: var(--muted); font-size: 13px; padding: 16px 0; }
+  </style>
+</head>
+<body>
+  <div class="wrap">
+    <div class="head">
+      <div>
+        <h2 style="margin:0 0 4px;">DroneDetector Inference Viewer</h2>
+        <div class="meta">Latest inference card per frequency. Browser keeps last 20 results per frequency.</div>
+      </div>
+      <div class="actions">
+        <div class="meta" id="ws-status">connecting...</div>
+        <button id="pause-btn" class="primary">Pause updates</button>
+      </div>
+    </div>
+    <div class="grid" id="cards"></div>
+  </div>
+
+<script>
+const MAX_RESULTS = 20;
+const state = {};
+const selected = {};
+let paused = false;
+let wsKeepalive = null;
+
+function freqSort(a, b) { return Number(a) - Number(b); }
+function formatTs(ts) {
+  return new Date(Number(ts) * 1000).toLocaleString('ru-RU', { hour12: false });
+}
+function escapeHtml(value) {
+  return String(value ?? '').replaceAll('&', '&amp;').replaceAll('<', '&lt;').replaceAll('>', '&gt;').replaceAll('"', '&quot;');
+}
+function imageUrl(name) {
+  return `/inference/images/${encodeURIComponent(name)}`;
+}
+function primaryImage(result) {
+  return (result.images || [])[0] || '';
+}
+function trimResults(freq) {
+  const arr = state[freq] || [];
+  state[freq] = arr.slice(-MAX_RESULTS);
+}
+function ensureCard(freq) {
+  if (document.getElementById(`card-${freq}`)) return;
+  const card = document.createElement('div');
+  card.className = 'card';
+  card.id = `card-${freq}`;
+  card.innerHTML = `
+    <div class="card-head">
+      <div class="freq">${escapeHtml(freq)} MHz</div>
+      <div class="pill ${paused ? 'paused' : 'live'}" id="badge-${freq}">${paused ? 'paused' : 'live'}</div>
+    </div>
+    <div class="summary" id="summary-${freq}"></div>
+    <div class="images" id="images-${freq}"></div>
+    <div class="history-title">Recent results</div>
+    <div class="history" id="history-${freq}"></div>
+  `;
+  document.getElementById('cards').appendChild(card);
+}
+function renderSummary(freq, result) {
+  const el = document.getElementById(`summary-${freq}`);
+  el.innerHTML = `
+    <div class="summary-item"><div class="summary-label">Model</div><div class="summary-value">${escapeHtml(result.model)}</div></div>
+    <div class="summary-item"><div class="summary-label">Prediction</div><div class="summary-value">${escapeHtml(result.prediction)}</div></div>
+    <div class="summary-item"><div class="summary-label">Confidence</div><div class="summary-value">${Number(result.probability).toFixed(3)}</div></div>
+    <div class="summary-item"><div class="summary-label">Time</div><div class="summary-value">${escapeHtml(formatTs(result.ts))}</div></div>
+  `;
+}
+function renderImages(freq, result) {
+  const el = document.getElementById(`images-${freq}`);
+  const images = result.images || [];
+  if (!images.length) {
+    el.innerHTML = '<div class="empty">No images for this inference.</div>';
+    return;
+  }
+  el.innerHTML = images.map((name) => `
+    <div class="image-card">
+      <img loading="lazy" src="${imageUrl(name)}" alt="${escapeHtml(name)}" />
+      <div class="cap">${escapeHtml(name)}</div>
+    </div>
+  `).join('');
+}
+function renderHistory(freq) {
+  const el = document.getElementById(`history-${freq}`);
+  const results = state[freq] || [];
+  if (!results.length) {
+    el.innerHTML = '<div class="empty">No results yet.</div>';
+    return;
+  }
+  el.innerHTML = results.slice().reverse().map((result) => {
+    const active = String(selected[freq]) === String(result.result_id) ? 'active' : '';
+    const image = primaryImage(result);
+    return `
+      <button class="thumb ${active}" data-freq="${escapeHtml(freq)}" data-result-id="${result.result_id}">
+        ${image ? `<img loading="lazy" src="${imageUrl(image)}" alt="${escapeHtml(result.prediction)}" />` : '<div class="empty" style="padding:20px 0;">no image</div>'}
+        <div class="t1">${escapeHtml(result.prediction)}</div>
+        <div class="t2">p=${Number(result.probability).toFixed(2)}</div>
+      </button>
+    `;
+  }).join('');
+  el.querySelectorAll('.thumb').forEach((node) => {
+    node.addEventListener('click', () => {
+      selected[freq] = Number(node.dataset.resultId);
+      render(freq);
+    });
+  });
+}
+function render(freq) {
+  ensureCard(freq);
+  trimResults(freq);
+  const badge = document.getElementById(`badge-${freq}`);
+  badge.textContent = paused ? 'paused' : 'live';
+  badge.className = `pill ${paused ? 'paused' : 'live'}`;
+
+  const results = state[freq] || [];
+  if (!results.length) {
+    document.getElementById(`summary-${freq}`).innerHTML = '<div class="empty">No inference results yet.</div>';
+    document.getElementById(`images-${freq}`).innerHTML = '';
+    document.getElementById(`history-${freq}`).innerHTML = '';
+    return;
+  }
+  const active = results.find((item) => String(item.result_id) === String(selected[freq])) || results[results.length - 1];
+  selected[freq] = active.result_id;
+  renderSummary(freq, active);
+  renderImages(freq, active);
+  renderHistory(freq);
+}
+function renderAll() {
+  Object.keys(state).sort(freqSort).forEach(render);
+}
+function applySnapshot(series) {
+  const next = {};
+  for (const [freq, results] of Object.entries(series || {})) {
+    next[String(freq)] = Array.isArray(results) ? results.slice(-MAX_RESULTS) : [];
+  }
+  for (const freq of Object.keys(next)) {
+    state[freq] = next[freq];
+    if (state[freq].length) {
+      selected[freq] = state[freq][state[freq].length - 1].result_id;
+    }
+  }
+  renderAll();
+}
+function ingestResult(result) {
+  const freq = String(result.freq);
+  if (!state[freq]) state[freq] = [];
+  state[freq].push(result);
+  trimResults(freq);
+  selected[freq] = result.result_id;
+  render(freq);
+}
+async function loadHistory() {
+  const res = await fetch(`/inference/history?limit=${MAX_RESULTS}`);
+  const payload = await res.json();
+  applySnapshot(payload.series || {});
+}
+function setPaused(nextPaused) {
+  paused = nextPaused;
+  const btn = document.getElementById('pause-btn');
+  btn.textContent = paused ? 'Resume updates' : 'Pause updates';
+  btn.className = paused ? '' : 'primary';
+  renderAll();
+}
+function connectWs() {
+  const proto = location.protocol === 'https:' ? 'wss' : 'ws';
+  const ws = new WebSocket(`${proto}://${location.host}/inference/ws`);
+  ws.onopen = () => {
+    document.getElementById('ws-status').textContent = paused ? 'ws connected (paused)' : 'ws connected';
+    if (wsKeepalive) clearInterval(wsKeepalive);
+    wsKeepalive = setInterval(() => {
+      if (ws.readyState === 1) ws.send('ping');
+    }, 20000);
+  };
+  ws.onmessage = (event) => {
+    const msg = JSON.parse(event.data);
+    if (msg.type === 'snapshot' && msg.data) {
+      if (!paused) applySnapshot(msg.data);
+      return;
+    }
+    if (msg.type !== 'inference_result' || paused) return;
+    ingestResult(msg.data);
+  };
+  ws.onclose = () => {
+    document.getElementById('ws-status').textContent = 'ws disconnected, retrying...';
+    if (wsKeepalive) clearInterval(wsKeepalive);
+    setTimeout(connectWs, 1500);
+  };
+  ws.onerror = () => {
+    document.getElementById('ws-status').textContent = 'ws error';
+  };
+}
+document.getElementById('pause-btn').addEventListener('click', async () => {
+  if (paused) {
+    setPaused(false);
+    document.getElementById('ws-status').textContent = 'syncing...';
+    try {
+      await loadHistory();
+      document.getElementById('ws-status').textContent = 'ws connected';
+    } catch (err) {
+      document.getElementById('ws-status').textContent = `history error: ${err}`;
+    }
+  } else {
+    setPaused(true);
+    document.getElementById('ws-status').textContent = 'ws connected (paused)';
+  }
+});
+loadHistory().then(connectWs).catch((err) => {
+  document.getElementById('ws-status').textContent = `init error: ${err}`;
+  connectWs();
+});
+</script>
+</body>
+</html>
+"""
+
+
 @app.get('/', response_class=HTMLResponse)
 @app.get('/monitor', response_class=HTMLResponse)
 async def monitor_page():
     return HTMLResponse(content=MONITOR_HTML)
 
 
+@app.get('/inference-viewer', response_class=HTMLResponse)
+async def inference_viewer_page():
+    return HTMLResponse(content=INFERENCE_VIEWER_HTML)
+
+
+@app.get('/inference/images/{filename}')
+async def inference_image(filename: str):
+    safe_name = Path(filename).name
+    if safe_name != filename:
+        raise HTTPException(status_code=404, detail='image not found')
+
+    image_path = (INFERENCE_RESULT_DIR / safe_name).resolve()
+    if image_path.parent != INFERENCE_RESULT_DIR or not image_path.is_file():
+        raise HTTPException(status_code=404, detail='image not found')
+
+    return FileResponse(image_path)
+
+
 if __name__ == '__main__':
     import uvicorn
 

train_scripts/ImageDatasetCreate_spec_imag_real_1200.ipynb

@@ -0,0 +1,284 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x272800ef510>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "import torchsig.utils as u\n",
+    "import torchsig.transforms.transforms as T\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4848b066-2e09-4c1c-b8fa-8e3fa84d907a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "s = T.Spectrogram(nperseg=1024)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, specT=None,figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        if specT is None:\n",
+    "            specT = T.Spectrogram(nperseg=1024)\n",
+    "        with open(path_to_data + filename, 'rb') as file:\n",
+    "            tmp = np.frombuffer(file.read(), dtype=np.complex64)\n",
+    "        signal = tmp\n",
+    "        spectr = np.array(specT(signal)['data']['samples'][:,:figsize[0] * dpi])\n",
+    "        mag = np.abs(signal)\n",
+    "        real = signal.real\n",
+    "\n",
+    "        fig2 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(real, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf2 = io.BytesIO()\n",
+    "        fig2.savefig(buf2, format=\"png\", dpi=dpi)\n",
+    "        buf2.seek(0)\n",
+    "        img_arr2 = np.frombuffer(buf2.getvalue(), dtype=np.uint8)\n",
+    "        buf2.close()\n",
+    "        img2 = cv2.imdecode(img_arr2, 1)\n",
+    "        img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig2)\n",
+    "\n",
+    "        fig3 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(mag, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf3 = io.BytesIO()\n",
+    "        fig3.savefig(buf3, format=\"png\", dpi=dpi)\n",
+    "        buf3.seek(0)\n",
+    "        img_arr3 = np.frombuffer(buf3.getvalue(), dtype=np.uint8)\n",
+    "        buf3.close()\n",
+    "        img3 = cv2.imdecode(img_arr3, 1)\n",
+    "        img3 = cv2.cvtColor(img3, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig3)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(img2, resize)\n",
+    "            resized_mag = cv2.resize(img3, resize)\n",
+    "            resized_spectr = cv2.resize(spectr, resize)\n",
+    "            img = np.asarray([resized_real, resized_mag, resized_spectr], dtype=np.float32)\n",
+    "            return img\n",
+    "        img = np.asarray([img2, img3, spectr], dtype=np.float32)\n",
+    "        return img\n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = '//192.168.11.63/data/DATASETS/Energomash/1200'\n",
+    "path_to_pictures = '//192.168.11.63/data/DATASETS/Energomash/1200_jpg'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|                                                                                          | 0/963 [00:00<?, ?it/s]C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\scipy\\signal\\_spectral_py.py:1936: RuntimeWarning: overflow encountered in multiply\n",
+      "  result = np.conjugate(result) * result\n",
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\scipy\\signal\\_spectral_py.py:1938: RuntimeWarning: invalid value encountered in multiply\n",
+      "  result *= scale\n",
+      "100%|████████████████████████████████████████████████████████████████████████████████| 963/963 [17:40<00:00,  1.10s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  drone  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 963/963 [51:41<00:00,  3.22s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  noise  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath = path_to_pictures +'/' + subdir + '/' + file + '.npy'\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.png' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.png' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.png'\n",
+    "        if not os.path.exists(savepath):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, specT=s, resize = size)\n",
+    "            gc.collect()\n",
+    "            try:\n",
+    "                \n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                np.save(savepath, img)\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f4bf849",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_2400.ipynb

@@ -0,0 +1,270 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x25775eabcd0>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "import torchsig.utils as u\n",
+    "import torchsig.transforms.transforms as T\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4848b066-2e09-4c1c-b8fa-8e3fa84d907a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "s = T.Spectrogram(nperseg=256)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, specT=None,figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        if specT is None:\n",
+    "            specT = T.Spectrogram(nperseg=256)\n",
+    "        with open(path_to_data + filename, 'rb') as file:\n",
+    "            tmp = np.frombuffer(file.read(), dtype=np.complex64)\n",
+    "        signal = tmp\n",
+    "        spectr = np.array(specT(signal)['data']['samples'][:,:figsize[0] * dpi])\n",
+    "        mag = np.abs(signal)\n",
+    "        real = signal.real\n",
+    "\n",
+    "        fig2 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(real, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf2 = io.BytesIO()\n",
+    "        fig2.savefig(buf2, format=\"png\", dpi=dpi)\n",
+    "        buf2.seek(0)\n",
+    "        img_arr2 = np.frombuffer(buf2.getvalue(), dtype=np.uint8)\n",
+    "        buf2.close()\n",
+    "        img2 = cv2.imdecode(img_arr2, 1)\n",
+    "        img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig2)\n",
+    "\n",
+    "        fig3 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(mag, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf3 = io.BytesIO()\n",
+    "        fig3.savefig(buf3, format=\"png\", dpi=dpi)\n",
+    "        buf3.seek(0)\n",
+    "        img_arr3 = np.frombuffer(buf3.getvalue(), dtype=np.uint8)\n",
+    "        buf3.close()\n",
+    "        img3 = cv2.imdecode(img_arr3, 1)\n",
+    "        img3 = cv2.cvtColor(img3, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig3)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(img2, resize)\n",
+    "            resized_mag = cv2.resize(img3, resize)\n",
+    "            resized_spectr = cv2.resize(spectr, resize)\n",
+    "            img = np.asarray([resized_real, resized_mag, resized_spectr], dtype=np.float32)\n",
+    "            return img\n",
+    "        img = np.asarray([img2, img3, spectr], dtype=np.float32)\n",
+    "        return img\n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = '//192.168.11.63/data/DATASETS/Energomash/2400'\n",
+    "path_to_pictures = '//192.168.11.63/data/DATASETS/Energomash/2400_jpg'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|                                                                                          | 0/965 [00:00<?, ?it/s]C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\scipy\\signal\\_spectral_py.py:1936: RuntimeWarning: overflow encountered in multiply\n",
+      "  result = np.conjugate(result) * result\n",
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\scipy\\signal\\_spectral_py.py:1938: RuntimeWarning: invalid value encountered in multiply\n",
+      "  result *= scale\n",
+      "100%|████████████████████████████████████████████████████████████████████████████████| 965/965 [28:11<00:00,  1.75s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  noise  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath = path_to_pictures +'/' + subdir + '/' + file + '.npy'\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.png' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.png' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.png'\n",
+    "        if not os.path.exists(savepath):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, specT=s, resize = size)\n",
+    "            gc.collect()\n",
+    "            try:\n",
+    "                \n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                np.save(savepath, img)\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "106b1add",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_5800.ipynb

@@ -0,0 +1,270 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x25775eabcd0>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "import torchsig.utils as u\n",
+    "import torchsig.transforms.transforms as T\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4848b066-2e09-4c1c-b8fa-8e3fa84d907a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "s = T.Spectrogram(nperseg=256)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, specT=None,figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        if specT is None:\n",
+    "            specT = T.Spectrogram(nperseg=256)\n",
+    "        with open(path_to_data + filename, 'rb') as file:\n",
+    "            tmp = np.frombuffer(file.read(), dtype=np.complex64)\n",
+    "        signal = tmp\n",
+    "        spectr = np.array(specT(signal)['data']['samples'][:,:figsize[0] * dpi])\n",
+    "        mag = np.abs(signal)\n",
+    "        real = signal.real\n",
+    "\n",
+    "        fig2 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(real, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf2 = io.BytesIO()\n",
+    "        fig2.savefig(buf2, format=\"png\", dpi=dpi)\n",
+    "        buf2.seek(0)\n",
+    "        img_arr2 = np.frombuffer(buf2.getvalue(), dtype=np.uint8)\n",
+    "        buf2.close()\n",
+    "        img2 = cv2.imdecode(img_arr2, 1)\n",
+    "        img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig2)\n",
+    "\n",
+    "        fig3 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(mag, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf3 = io.BytesIO()\n",
+    "        fig3.savefig(buf3, format=\"png\", dpi=dpi)\n",
+    "        buf3.seek(0)\n",
+    "        img_arr3 = np.frombuffer(buf3.getvalue(), dtype=np.uint8)\n",
+    "        buf3.close()\n",
+    "        img3 = cv2.imdecode(img_arr3, 1)\n",
+    "        img3 = cv2.cvtColor(img3, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig3)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(img2, resize)\n",
+    "            resized_mag = cv2.resize(img3, resize)\n",
+    "            resized_spectr = cv2.resize(spectr, resize)\n",
+    "            img = np.asarray([resized_real, resized_mag, resized_spectr], dtype=np.float32)\n",
+    "            return img\n",
+    "        img = np.asarray([img2, img3, spectr], dtype=np.float32)\n",
+    "        return img\n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = '//192.168.11.63/data/DATASETS/Energomash/2400'\n",
+    "path_to_pictures = '//192.168.11.63/data/DATASETS/Energomash/2400_jpg'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|                                                                                          | 0/965 [00:00<?, ?it/s]C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\scipy\\signal\\_spectral_py.py:1936: RuntimeWarning: overflow encountered in multiply\n",
+      "  result = np.conjugate(result) * result\n",
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\scipy\\signal\\_spectral_py.py:1938: RuntimeWarning: invalid value encountered in multiply\n",
+      "  result *= scale\n",
+      "100%|████████████████████████████████████████████████████████████████████████████████| 965/965 [28:11<00:00,  1.75s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  noise  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath = path_to_pictures +'/' + subdir + '/' + file + '.npy'\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.png' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.png' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.png'\n",
+    "        if not os.path.exists(savepath):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, specT=s, resize = size)\n",
+    "            gc.collect()\n",
+    "            try:\n",
+    "                \n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                np.save(savepath, img)\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "106b1add",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_915-Copy1.ipynb

@@ -0,0 +1,428 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x73285e4f6300>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "import torchsig.utils as u\n",
+    "import torchsig.transforms.transforms as T\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4848b066-2e09-4c1c-b8fa-8e3fa84d907a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "s = T.Spectrogram(nperseg=256)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, specT=None, figsize=(16,16), dpi=16, resize = None):\n",
+    "    def standartize_signal(signal):\n",
+    "        mean = np.mean(signal)\n",
+    "        std = np.std(signal)\n",
+    "        standardized_signal = (signal - mean) / std\n",
+    "        return standardized_signal\n",
+    "    \n",
+    "    try:\n",
+    "        if specT is None:\n",
+    "            specT = T.Spectrogram(nperseg=256)\n",
+    "        with open(path_to_data + filename, 'rb') as file:\n",
+    "            tmp = np.frombuffer(file.read(), dtype=np.complex64)\n",
+    "        signal = tmp\n",
+    "        print(len(signal))\n",
+    "        spectr = np.array(specT(signal)['data']['samples'][:,:figsize[0] * dpi])\n",
+    "        mag = np.abs(signal)\n",
+    "        mag = standartize_signal(mag)\n",
+    "        real = signal.real\n",
+    "        real = standartize_signal(real)\n",
+    "\n",
+    "        fig2 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(real, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf2 = io.BytesIO()\n",
+    "        fig2.savefig(buf2, format=\"png\", dpi=dpi)\n",
+    "        buf2.seek(0)\n",
+    "        img_arr2 = np.frombuffer(buf2.getvalue(), dtype=np.uint8)\n",
+    "        buf2.close()\n",
+    "        img2 = cv2.imdecode(img_arr2, 1)\n",
+    "        img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig2)\n",
+    "\n",
+    "        fig3 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "\n",
+    "        plt.plot(mag, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf3 = io.BytesIO()\n",
+    "        fig3.savefig(buf3, format=\"png\", dpi=dpi)\n",
+    "        buf3.seek(0)\n",
+    "        img_arr3 = np.frombuffer(buf3.getvalue(), dtype=np.uint8)\n",
+    "        buf3.close()\n",
+    "        img3 = cv2.imdecode(img_arr3, 1)\n",
+    "        img3 = cv2.cvtColor(img3, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig3)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(img2, resize)\n",
+    "            resized_mag = cv2.resize(img3, resize)\n",
+    "            resized_spectr = cv2.resize(spectr, resize)\n",
+    "            img = np.asarray([resized_real, resized_mag, resized_spectr], dtype=np.float32)\n",
+    "            return img\n",
+    "        img = np.asarray([img2, img3, spectr], dtype=np.float32)\n",
+    "        return img\n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None\n",
+    "\n",
+    "def plot_signal_and_magnitude(path_to_data, filename, filename_signal):\n",
+    "    def remove_outliers(signal, threshold):\n",
+    "        filtered_signal = np.where(np.abs(signal) <= threshold, signal, np.nan)\n",
+    "        return np.nan_to_num(filtered_signal)\n",
+    "    \n",
+    "    def standartize_signal(signal):\n",
+    "        mean = np.mean(signal)\n",
+    "        std = np.std(signal)\n",
+    "        standardized_signal = (signal - mean) / std\n",
+    "        return standardized_signal\n",
+    "    \n",
+    "    with open(path_to_data + filename, 'rb') as file:\n",
+    "        signal = np.frombuffer(file.read(), dtype=np.complex64)\n",
+    "    print(max(np.real(signal)))\n",
+    "    print(signal[:100])\n",
+    "    plt.figure(figsize=(12, 6))\n",
+    "    plt.subplot(2, 1, 1)\n",
+    "    plt.plot(remove_outliers(standartize_signal(np.real(signal)),1)[10000:], label='Real Part')\n",
+    "    plt.plot(remove_outliers(standartize_signal(np.imag(signal)),1)[10000:], label='Imaginary Part')\n",
+    "    plt.title('QAM Signal')\n",
+    "    plt.legend()\n",
+    "    plt.subplot(2, 1, 2)\n",
+    "    plt.plot(np.abs(signal), label='Magnitude')\n",
+    "    plt.title('Magnitude of QAM Signal')\n",
+    "    plt.legend()\n",
+    "    plt.tight_layout()\n",
+    "    plt.savefig(filename_signal)\n",
+    "    plt.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = '/home/sibscience/Datasets/915_9K'\n",
+    "path_to_pictures = '/home/sibscience/Datasets/915_9K_jpg'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "6a5f4c51",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: '/home/sibscience/Datasets/915_9K_jpg'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mFileNotFoundError\u001b[39m                         Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[7]\u001b[39m\u001b[32m, line 3\u001b[39m\n\u001b[32m      1\u001b[39m size = (\u001b[32m256\u001b[39m,\u001b[32m256\u001b[39m)\n\u001b[32m      2\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m os.path.exists(path_to_pictures):\n\u001b[32m----> \u001b[39m\u001b[32m3\u001b[39m     \u001b[43mos\u001b[49m\u001b[43m.\u001b[49m\u001b[43mmkdir\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath_to_pictures\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m      4\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m subdir \u001b[38;5;129;01min\u001b[39;00m os.listdir(path_to_binaries):\n\u001b[32m      5\u001b[39m     filepath = path_to_binaries + \u001b[33m'\u001b[39m\u001b[33m/\u001b[39m\u001b[33m'\u001b[39m + subdir + \u001b[33m'\u001b[39m\u001b[33m/\u001b[39m\u001b[33m'\u001b[39m\n",
+      "\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: '/home/sibscience/Datasets/915_9K_jpg'"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath = path_to_pictures +'/' + subdir + '/' + file + '.npy'\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '.png' \n",
+    "        if not os.path.exists(savepath):\n",
+    "            img = plot_signal_and_magnitude(path_to_data=filepath, filename=file, filename_signal= savepath_real_png)\n",
+    "            gc.collect()\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r\n",
+      "  0%|                                                                                          | 0/565 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "800016\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r\n",
+      " 28%|█████████████████████▉                                                         | 157/565 [00:01<00:02, 145.94it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n",
+      "800016\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r\n",
+      " 30%|████████████████████████▎                                                       | 172/565 [00:15<00:46,  8.38it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "800016\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 31%|████████████████████████▍                                                       | 173/565 [00:16<00:37, 10.59it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "800016\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[10], line 15\u001b[0m\n\u001b[0;32m     13\u001b[0m savepath_spec_png \u001b[38;5;241m=\u001b[39m path_to_pictures \u001b[38;5;241m+\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;241m+\u001b[39m subdir \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;241m+\u001b[39m file \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_spec\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.png\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m     14\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mexists(savepath):\n\u001b[1;32m---> 15\u001b[0m     img \u001b[38;5;241m=\u001b[39m \u001b[43msig2pic_with_spec\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath_to_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilepath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfile\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mspecT\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresize\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43msize\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     16\u001b[0m     gc\u001b[38;5;241m.\u001b[39mcollect()\n\u001b[0;32m     17\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n",
+      "Cell \u001b[1;32mIn[7], line 29\u001b[0m, in \u001b[0;36msig2pic_with_spec\u001b[1;34m(path_to_data, filename, specT, figsize, dpi, resize)\u001b[0m\n\u001b[0;32m     27\u001b[0m plt\u001b[38;5;241m.\u001b[39mmargins(\u001b[38;5;241m0\u001b[39m,\u001b[38;5;241m0\u001b[39m)\n\u001b[0;32m     28\u001b[0m buf2 \u001b[38;5;241m=\u001b[39m io\u001b[38;5;241m.\u001b[39mBytesIO()\n\u001b[1;32m---> 29\u001b[0m \u001b[43mfig2\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msavefig\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbuf2\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mformat\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpng\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdpi\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdpi\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     30\u001b[0m buf2\u001b[38;5;241m.\u001b[39mseek(\u001b[38;5;241m0\u001b[39m)\n\u001b[0;32m     31\u001b[0m img_arr2 \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mfrombuffer(buf2\u001b[38;5;241m.\u001b[39mgetvalue(), dtype\u001b[38;5;241m=\u001b[39mnp\u001b[38;5;241m.\u001b[39muint8)\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\figure.py:3390\u001b[0m, in \u001b[0;36mFigure.savefig\u001b[1;34m(self, fname, transparent, **kwargs)\u001b[0m\n\u001b[0;32m   3388\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m ax \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes:\n\u001b[0;32m   3389\u001b[0m         _recursively_make_axes_transparent(stack, ax)\n\u001b[1;32m-> 3390\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcanvas\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mprint_figure\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\backend_bases.py:2193\u001b[0m, in \u001b[0;36mFigureCanvasBase.print_figure\u001b[1;34m(self, filename, dpi, facecolor, edgecolor, orientation, format, bbox_inches, pad_inches, bbox_extra_artists, backend, **kwargs)\u001b[0m\n\u001b[0;32m   2189\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   2190\u001b[0m     \u001b[38;5;66;03m# _get_renderer may change the figure dpi (as vector formats\u001b[39;00m\n\u001b[0;32m   2191\u001b[0m     \u001b[38;5;66;03m# force the figure dpi to 72), so we need to set it again here.\u001b[39;00m\n\u001b[0;32m   2192\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m cbook\u001b[38;5;241m.\u001b[39m_setattr_cm(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfigure, dpi\u001b[38;5;241m=\u001b[39mdpi):\n\u001b[1;32m-> 2193\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43mprint_method\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   2194\u001b[0m \u001b[43m            \u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2195\u001b[0m \u001b[43m            \u001b[49m\u001b[43mfacecolor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfacecolor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2196\u001b[0m \u001b[43m            \u001b[49m\u001b[43medgecolor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43medgecolor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2197\u001b[0m \u001b[43m            \u001b[49m\u001b[43morientation\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morientation\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2198\u001b[0m \u001b[43m            \u001b[49m\u001b[43mbbox_inches_restore\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_bbox_inches_restore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   2199\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   2200\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m   2201\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m bbox_inches \u001b[38;5;129;01mand\u001b[39;00m restore_bbox:\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\backend_bases.py:2043\u001b[0m, in \u001b[0;36mFigureCanvasBase._switch_canvas_and_return_print_method.<locals>.<lambda>\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m   2039\u001b[0m     optional_kws \u001b[38;5;241m=\u001b[39m {  \u001b[38;5;66;03m# Passed by print_figure for other renderers.\u001b[39;00m\n\u001b[0;32m   2040\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdpi\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfacecolor\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124medgecolor\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124morientation\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   2041\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbbox_inches_restore\u001b[39m\u001b[38;5;124m\"\u001b[39m}\n\u001b[0;32m   2042\u001b[0m     skip \u001b[38;5;241m=\u001b[39m optional_kws \u001b[38;5;241m-\u001b[39m {\u001b[38;5;241m*\u001b[39minspect\u001b[38;5;241m.\u001b[39msignature(meth)\u001b[38;5;241m.\u001b[39mparameters}\n\u001b[1;32m-> 2043\u001b[0m     print_method \u001b[38;5;241m=\u001b[39m functools\u001b[38;5;241m.\u001b[39mwraps(meth)(\u001b[38;5;28;01mlambda\u001b[39;00m \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: \u001b[43mmeth\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   2044\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mskip\u001b[49m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[0;32m   2045\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:  \u001b[38;5;66;03m# Let third-parties do as they see fit.\u001b[39;00m\n\u001b[0;32m   2046\u001b[0m     print_method \u001b[38;5;241m=\u001b[39m meth\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\backends\\backend_agg.py:497\u001b[0m, in \u001b[0;36mFigureCanvasAgg.print_png\u001b[1;34m(self, filename_or_obj, metadata, pil_kwargs)\u001b[0m\n\u001b[0;32m    450\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mprint_png\u001b[39m(\u001b[38;5;28mself\u001b[39m, filename_or_obj, \u001b[38;5;241m*\u001b[39m, metadata\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, pil_kwargs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[0;32m    451\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    452\u001b[0m \u001b[38;5;124;03m    Write the figure to a PNG file.\u001b[39;00m\n\u001b[0;32m    453\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    495\u001b[0m \u001b[38;5;124;03m        *metadata*, including the default 'Software' key.\u001b[39;00m\n\u001b[0;32m    496\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m--> 497\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_print_pil\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilename_or_obj\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpng\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpil_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\backends\\backend_agg.py:445\u001b[0m, in \u001b[0;36mFigureCanvasAgg._print_pil\u001b[1;34m(self, filename_or_obj, fmt, pil_kwargs, metadata)\u001b[0m\n\u001b[0;32m    440\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_print_pil\u001b[39m(\u001b[38;5;28mself\u001b[39m, filename_or_obj, fmt, pil_kwargs, metadata\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[0;32m    441\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    442\u001b[0m \u001b[38;5;124;03m    Draw the canvas, then save it using `.image.imsave` (to which\u001b[39;00m\n\u001b[0;32m    443\u001b[0m \u001b[38;5;124;03m    *pil_kwargs* and *metadata* are forwarded).\u001b[39;00m\n\u001b[0;32m    444\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m--> 445\u001b[0m     \u001b[43mFigureCanvasAgg\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m    446\u001b[0m     mpl\u001b[38;5;241m.\u001b[39mimage\u001b[38;5;241m.\u001b[39mimsave(\n\u001b[0;32m    447\u001b[0m         filename_or_obj, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuffer_rgba(), \u001b[38;5;28mformat\u001b[39m\u001b[38;5;241m=\u001b[39mfmt, origin\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mupper\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    448\u001b[0m         dpi\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfigure\u001b[38;5;241m.\u001b[39mdpi, metadata\u001b[38;5;241m=\u001b[39mmetadata, pil_kwargs\u001b[38;5;241m=\u001b[39mpil_kwargs)\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\backends\\backend_agg.py:388\u001b[0m, in \u001b[0;36mFigureCanvasAgg.draw\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    385\u001b[0m \u001b[38;5;66;03m# Acquire a lock on the shared font cache.\u001b[39;00m\n\u001b[0;32m    386\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtoolbar\u001b[38;5;241m.\u001b[39m_wait_cursor_for_draw_cm() \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtoolbar\n\u001b[0;32m    387\u001b[0m       \u001b[38;5;28;01melse\u001b[39;00m nullcontext()):\n\u001b[1;32m--> 388\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfigure\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrenderer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    389\u001b[0m     \u001b[38;5;66;03m# A GUI class may be need to update a window using this draw, so\u001b[39;00m\n\u001b[0;32m    390\u001b[0m     \u001b[38;5;66;03m# don't forget to call the superclass.\u001b[39;00m\n\u001b[0;32m    391\u001b[0m     \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mdraw()\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\artist.py:95\u001b[0m, in \u001b[0;36m_finalize_rasterization.<locals>.draw_wrapper\u001b[1;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[0;32m     93\u001b[0m \u001b[38;5;129m@wraps\u001b[39m(draw)\n\u001b[0;32m     94\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdraw_wrapper\u001b[39m(artist, renderer, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m---> 95\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[43martist\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     96\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m renderer\u001b[38;5;241m.\u001b[39m_rasterizing:\n\u001b[0;32m     97\u001b[0m         renderer\u001b[38;5;241m.\u001b[39mstop_rasterizing()\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\artist.py:72\u001b[0m, in \u001b[0;36mallow_rasterization.<locals>.draw_wrapper\u001b[1;34m(artist, renderer)\u001b[0m\n\u001b[0;32m     69\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m artist\u001b[38;5;241m.\u001b[39mget_agg_filter() \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m     70\u001b[0m         renderer\u001b[38;5;241m.\u001b[39mstart_filter()\n\u001b[1;32m---> 72\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[43martist\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     73\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m     74\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m artist\u001b[38;5;241m.\u001b[39mget_agg_filter() \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\figure.py:3154\u001b[0m, in \u001b[0;36mFigure.draw\u001b[1;34m(self, renderer)\u001b[0m\n\u001b[0;32m   3151\u001b[0m         \u001b[38;5;66;03m# ValueError can occur when resizing a window.\u001b[39;00m\n\u001b[0;32m   3153\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpatch\u001b[38;5;241m.\u001b[39mdraw(renderer)\n\u001b[1;32m-> 3154\u001b[0m \u001b[43mmimage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_draw_list_compositing_images\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   3155\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43martists\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msuppressComposite\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   3157\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sfig \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msubfigs:\n\u001b[0;32m   3158\u001b[0m     sfig\u001b[38;5;241m.\u001b[39mdraw(renderer)\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\image.py:132\u001b[0m, in \u001b[0;36m_draw_list_compositing_images\u001b[1;34m(renderer, parent, artists, suppress_composite)\u001b[0m\n\u001b[0;32m    130\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m not_composite \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m has_images:\n\u001b[0;32m    131\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m artists:\n\u001b[1;32m--> 132\u001b[0m         \u001b[43ma\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    133\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    134\u001b[0m     \u001b[38;5;66;03m# Composite any adjacent images together\u001b[39;00m\n\u001b[0;32m    135\u001b[0m     image_group \u001b[38;5;241m=\u001b[39m []\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\artist.py:72\u001b[0m, in \u001b[0;36mallow_rasterization.<locals>.draw_wrapper\u001b[1;34m(artist, renderer)\u001b[0m\n\u001b[0;32m     69\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m artist\u001b[38;5;241m.\u001b[39mget_agg_filter() \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m     70\u001b[0m         renderer\u001b[38;5;241m.\u001b[39mstart_filter()\n\u001b[1;32m---> 72\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[43martist\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     73\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m     74\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m artist\u001b[38;5;241m.\u001b[39mget_agg_filter() \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\axes\\_base.py:3070\u001b[0m, in \u001b[0;36m_AxesBase.draw\u001b[1;34m(self, renderer)\u001b[0m\n\u001b[0;32m   3067\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m artists_rasterized:\n\u001b[0;32m   3068\u001b[0m     _draw_rasterized(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfigure, artists_rasterized, renderer)\n\u001b[1;32m-> 3070\u001b[0m \u001b[43mmimage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_draw_list_compositing_images\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   3071\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43martists\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfigure\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msuppressComposite\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   3073\u001b[0m renderer\u001b[38;5;241m.\u001b[39mclose_group(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124maxes\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m   3074\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstale \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\image.py:132\u001b[0m, in \u001b[0;36m_draw_list_compositing_images\u001b[1;34m(renderer, parent, artists, suppress_composite)\u001b[0m\n\u001b[0;32m    130\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m not_composite \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m has_images:\n\u001b[0;32m    131\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m artists:\n\u001b[1;32m--> 132\u001b[0m         \u001b[43ma\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    133\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    134\u001b[0m     \u001b[38;5;66;03m# Composite any adjacent images together\u001b[39;00m\n\u001b[0;32m    135\u001b[0m     image_group \u001b[38;5;241m=\u001b[39m []\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\artist.py:72\u001b[0m, in \u001b[0;36mallow_rasterization.<locals>.draw_wrapper\u001b[1;34m(artist, renderer)\u001b[0m\n\u001b[0;32m     69\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m artist\u001b[38;5;241m.\u001b[39mget_agg_filter() \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m     70\u001b[0m         renderer\u001b[38;5;241m.\u001b[39mstart_filter()\n\u001b[1;32m---> 72\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdraw\u001b[49m\u001b[43m(\u001b[49m\u001b[43martist\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrenderer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     73\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m     74\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m artist\u001b[38;5;241m.\u001b[39mget_agg_filter() \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\lines.py:801\u001b[0m, in \u001b[0;36mLine2D.draw\u001b[1;34m(self, renderer)\u001b[0m\n\u001b[0;32m    798\u001b[0m         gc\u001b[38;5;241m.\u001b[39mset_foreground(lc_rgba, isRGBA\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m    800\u001b[0m         gc\u001b[38;5;241m.\u001b[39mset_dashes(\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dash_pattern)\n\u001b[1;32m--> 801\u001b[0m         \u001b[43mrenderer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdraw_path\u001b[49m\u001b[43m(\u001b[49m\u001b[43mgc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maffine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrozen\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    802\u001b[0m         gc\u001b[38;5;241m.\u001b[39mrestore()\n\u001b[0;32m    804\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_marker \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_markersize \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\matplotlib\\backends\\backend_agg.py:117\u001b[0m, in \u001b[0;36mRendererAgg.draw_path\u001b[1;34m(self, gc, path, transform, rgbFace)\u001b[0m\n\u001b[0;32m    115\u001b[0m p\u001b[38;5;241m.\u001b[39msimplify_threshold \u001b[38;5;241m=\u001b[39m path\u001b[38;5;241m.\u001b[39msimplify_threshold\n\u001b[0;32m    116\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 117\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_renderer\u001b[38;5;241m.\u001b[39mdraw_path(gc, p, transform, rgbFace)\n\u001b[0;32m    118\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mOverflowError\u001b[39;00m:\n\u001b[0;32m    119\u001b[0m     msg \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m    120\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExceeded cell block limit in Agg.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    121\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPlease reduce the value of \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    127\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath\u001b[38;5;241m.\u001b[39msimplify_threshold\u001b[38;5;132;01m:\u001b[39;00m\u001b[38;5;124m.2f\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m on the input).\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    128\u001b[0m     )\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath = path_to_pictures +'/' + subdir + '/' + file + '.npy'\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.png' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.png' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.png'\n",
+    "        if not os.path.exists(savepath):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, specT=s, resize = size)\n",
+    "            gc.collect()\n",
+    "            try:\n",
+    "                \n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                np.save(savepath, img)\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "58ff5fbd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f9ad366",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv-train",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_915.ipynb

@@ -2,10 +2,18 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/sibscience-4/from_ssh/DroneDetector/.venv-train/lib/python3.12/site-packages/matplotlib/projections/__init__.py:63: UserWarning: Unable to import Axes3D. This may be due to multiple versions of Matplotlib being installed (e.g. as a system package and as a pip package). As a result, the 3D projection is not available.\n",
+      "  warnings.warn(\"Unable to import Axes3D. This may be due to multiple versions of \"\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -16,10 +24,10 @@
     {
      "data": {
       "text/plain": [
-       "<contextlib.ExitStack at 0x76adb5fa4260>"
+       "<contextlib.ExitStack at 0x7dbe9e0bc080>"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -64,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "4848b066-2e09-4c1c-b8fa-8e3fa84d907a",
    "metadata": {},
    "outputs": [],
@@ -74,7 +82,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "9267fbe1",
    "metadata": {},
    "outputs": [],
@@ -147,20 +155,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "selected_freq=915\n",
+    "selected_freq=2400\n",
     "\n",
-    "path_to_binaries = f'/home/sibsci/dataset/drone/{selected_freq}'\n",
-    "path_to_pictures = f'/home/sibsci/dataset_img/drone/{selected_freq}_jpg'"
+    "path_to_binaries = f'/mnt/data/Dataset/noise/{selected_freq}'\n",
+    "path_to_pictures = f'/mnt/data/Dataset_img/noise/{selected_freq}_jpg'"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 14,
    "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
    "metadata": {},
    "outputs": [],
@@ -170,7 +178,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 17,
    "id": "6f226f86-5d72-4573-8af6-750128b70263",
    "metadata": {},
    "outputs": [
@@ -178,14 +186,42 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2026-04-06_11-37-43: 100%|██████████| 42/42 [00:11<00:00,  3.55it/s]"
+      "2026-04-08_18-06-46: 100%|██████████| 1013/1013 [19:43<00:00,  1.17s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  2026-04-08_18-06-46  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2026-04-08_18-10-32: 100%|██████████| 353/353 [06:53<00:00,  1.17s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  2026-04-08_18-10-32  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2026-04-08_18-08-39: 100%|██████████| 1017/1017 [19:48<00:00,  1.17s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Dir:  2026-04-06_11-37-43  finished!\n"
+      "Dir:  2026-04-08_18-08-39  finished!\n"
      ]
     },
     {
@@ -200,7 +236,7 @@
     "size = (256,256)\n",
     "\n",
     "if not os.path.exists(path_to_pictures):\n",
-    "    os.makedirs(path_to_pictures,exist_ok=True)\n",
+    "    os.mkdir(path_to_pictures)\n",
     "\n",
     "for subdir in os.listdir(path_to_binaries):\n",
     "    filepath = path_to_binaries + '/' + subdir + '/'\n",
@@ -209,7 +245,7 @@
     "        continue\n",
     "\n",
     "    files = os.listdir(filepath)\n",
-    "    k = max(1, int(len(files) * 0.04))\n",
+    "    k = max(1, int(len(files) * 1))\n",
     "    files = random.sample(files, k)\n",
     "    for file in tqdm(files, desc=subdir):\n",
     "        full_input_path = filepath + file\n",

train_scripts/ImageDatasetCreate_spec_imag_real_from_npy_to_jpg.ipynb

@@ -0,0 +1,222 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x249d580ff50>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        array = np.load(path_to_data+filename)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(array[0], resize)\n",
+    "            resized_mag = cv2.resize(array[1], resize)\n",
+    "            resized_spectr = cv2.resize(array[2], resize)\n",
+    "            img = np.asarray(array, dtype=np.float32)\n",
+    "            return img\n",
+    "        \n",
+    "        img = np.asarray(array, dtype=np.float32)\n",
+    "        return img\n",
+    "    \n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = 'C:/Users/snytk/Lerning_NN_for_work/datasets/2.4_learning'\n",
+    "path_to_pictures = 'C:/Users/snytk/Lerning_NN_for_work/datasets_jpg/2.4_jpg_learning'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████| 8751/8751 [1:01:54<00:00,  2.36it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  drone  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████████████████████████████████████████████████████████████████████| 11202/11202 [1:19:30<00:00,  2.35it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  noise  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.jpg' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.jpg' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.jpg'\n",
+    "        if not os.path.exists(savepath_real_png):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, resize = size)\n",
+    "            gc.collect()\n",
+    "            \n",
+    "            try:\n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cfbd309d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_from_npy_to_jpg_1.2.ipynb

@@ -0,0 +1,360 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x20af0408250>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        array = np.load(path_to_data+filename)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(array[0], resize)\n",
+    "            resized_mag = cv2.resize(array[1], resize)\n",
+    "            resized_spectr = cv2.resize(array[2], resize)\n",
+    "            img = np.asarray(array, dtype=np.float32)\n",
+    "            return img\n",
+    "        \n",
+    "        img = np.asarray(array, dtype=np.float32)\n",
+    "        return img\n",
+    "    \n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None\n",
+    "    \n",
+    "    \n",
+    "    \n",
+    "\n",
+    "def pre_func_ensemble(data=None, src ='', ind_inference=0):\n",
+    "    try:\n",
+    "        import matplotlib.pyplot as plt\n",
+    "        matplotlib.use('Agg')\n",
+    "        plt.ioff()\n",
+    "\n",
+    "        figsize = (16, 16)\n",
+    "        dpi = 16\n",
+    "\n",
+    "        signal = np.vectorize(complex)(data[0], data[1])\n",
+    "        #np.save(src + '_inference_2400_' + str(ind_inference) + '.npy', signal)\n",
+    "        spec = transform.Spectrogram(nperseg=256)\n",
+    "        spectr = np.array(spec(signal)[:,:figsize[0] * dpi])\n",
+    "        fig1 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "        sigr = signal.real\n",
+    "        sigi = signal.imag\n",
+    "        \n",
+    "        plt.plot(sigr, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf1 = io.BytesIO()\n",
+    "        fig1.savefig(buf1, format=\"png\", dpi=dpi)\n",
+    "        buf1.seek(0)\n",
+    "        img_arr1 = np.frombuffer(buf1.getvalue(), dtype=np.uint8)\n",
+    "        buf1.close()\n",
+    "        img1 = cv2.imdecode(img_arr1, 1)\n",
+    "        img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig1)\n",
+    "\n",
+    "        fig2 = plt.figure(figsize = figsize)\n",
+    "        plt.axes(ylim=(-1, 1))\n",
+    "        sigr = signal.real\n",
+    "        sigi = signal.imag\n",
+    "        \n",
+    "        plt.plot(sigi, color='black')\n",
+    "        plt.gca().set_axis_off()\n",
+    "        plt.subplots_adjust(top = 1, bottom = 0, right = 1, left = 0, hspace = 0, wspace = 0)\n",
+    "        plt.margins(0,0)\n",
+    "        buf = io.BytesIO()\n",
+    "        fig2.savefig(buf, format=\"png\", dpi=dpi)\n",
+    "        buf.seek(0)\n",
+    "        img_arr = np.frombuffer(buf.getvalue(), dtype=np.uint8)\n",
+    "        buf.close()\n",
+    "        img = cv2.imdecode(img_arr, 1)\n",
+    "        img2 = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n",
+    "        plt.clf()\n",
+    "        plt.cla()\n",
+    "        plt.close()\n",
+    "        plt.close(fig2)\n",
+    "\n",
+    "        img = np.array([img1, img2, spectr])\n",
+    " \n",
+    "        cv2.destroyAllWindows()\n",
+    "        del signal\n",
+    "        del spec\n",
+    "        del spectr\n",
+    "        del img1\n",
+    "        del img2\n",
+    "        del sigr\n",
+    "        del sigi\n",
+    "        del buf\n",
+    "        del buf1\n",
+    "        del img_arr\n",
+    "        del img_arr1\n",
+    "        cv2.destroyAllWindows()\n",
+    "        gc.collect()\n",
+    "\n",
+    "        print('Подготовка данных завершена')\n",
+    "        print()\n",
+    "        return img\n",
+    "\n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None\n",
+    "\n",
+    "\n",
+    "def build_func_ensemble(file_model='', file_config='', num_classes=None):\n",
+    "    try:\n",
+    "        import matplotlib.pyplot as plt\n",
+    "        matplotlib.use('Agg')\n",
+    "        plt.ioff()\n",
+    "        torch.cuda.empty_cache()\n",
+    "        model1 = models.resnet18(pretrained=False)\n",
+    "        model2 = models.resnet50(pretrained=False)\n",
+    "        model3 = models.resnet101(pretrained=False)\n",
+    "\n",
+    "        num_classes = 2\n",
+    "\n",
+    "        model1.fc = nn.Linear(model1.fc.in_features, num_classes)\n",
+    "        model2.fc = nn.Linear(model2.fc.in_features, num_classes)\n",
+    "        model3.fc = nn.Linear(model3.fc.in_features, num_classes)\n",
+    "\n",
+    "        class Ensemble(nn.Module):\n",
+    "            def __init__(self, model1, model2, model3):\n",
+    "                super(Ensemble, self).__init__()\n",
+    "                self.model1 = model1\n",
+    "                self.model2 = model2\n",
+    "                self.model3 = model3\n",
+    "                self.fc = nn.Linear(3 * num_classes, num_classes)\n",
+    "\n",
+    "            def forward(self, x):\n",
+    "                x1 = self.model1(x)\n",
+    "                x2 = self.model2(x)\n",
+    "                x3 = self.model3(x)\n",
+    "                x = torch.cat((x1, x2, x3), dim=1)\n",
+    "                x = self.fc(x)\n",
+    "                return x\n",
+    "\n",
+    "        model = Ensemble(model1, model2, model3)\n",
+    "\n",
+    "        device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
+    "        if device != 'cpu':\n",
+    "            model = model.to(device)\n",
+    "        model.load_state_dict(torch.load(file_model, map_location=device))\n",
+    "        model.eval()\n",
+    "\n",
+    "        cv2.destroyAllWindows()\n",
+    "        del model1\n",
+    "        del model2\n",
+    "        del model3\n",
+    "        gc.collect()\n",
+    "\n",
+    "        print('Инициализация модели завершена')\n",
+    "        print()\n",
+    "        return model\n",
+    "\n",
+    "    except Exception as exc:\n",
+    "        print(str(exc))\n",
+    "        return None\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = 'C:/Users/snytk/Lerning_NN_for_work/datasets/1.2_learning'\n",
+    "path_to_pictures = 'C:/Users/snytk/Lerning_NN_for_work/datasets_jpg/1.2_jpg_learning'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 963/963 [06:36<00:00,  2.43it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  drone  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████████████████████████████████████████████████████████████████████████| 1724/1724 [11:41<00:00,  2.46it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  noise  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.jpg' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.jpg' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.jpg'\n",
+    "        if not os.path.exists(savepath_real_png):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, resize = size)\n",
+    "            gc.collect()\n",
+    "            \n",
+    "            try:\n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "871d7ab6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_from_npy_to_jpg_2.4.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x249d580ff50>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        array = np.load(path_to_data+filename)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(array[0], resize)\n",
+    "            resized_mag = cv2.resize(array[1], resize)\n",
+    "            resized_spectr = cv2.resize(array[2], resize)\n",
+    "            img = np.asarray(array, dtype=np.float32)\n",
+    "            return img\n",
+    "        \n",
+    "        img = np.asarray(array, dtype=np.float32)\n",
+    "        return img\n",
+    "    \n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = 'C:/Users/snytk/Lerning_NN_for_work/datasets/2.4_learning'\n",
+    "path_to_pictures = 'C:/Users/snytk/Lerning_NN_for_work/datasets_jpg/2.4_jpg_learning'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  2%|█▍                                                                           | 158/8751 [01:06<1:01:14,  2.34it/s]"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.jpg' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.jpg' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.jpg'\n",
+    "        if not os.path.exists(savepath_real_png):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, resize = size)\n",
+    "            gc.collect()\n",
+    "            \n",
+    "            try:\n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "871d7ab6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_from_npy_to_jpg_2_4_Copy1.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x249d580ff50>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        array = np.load(path_to_data+filename)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(array[0], resize)\n",
+    "            resized_mag = cv2.resize(array[1], resize)\n",
+    "            resized_spectr = cv2.resize(array[2], resize)\n",
+    "            img = np.asarray(array, dtype=np.float32)\n",
+    "            return img\n",
+    "        \n",
+    "        img = np.asarray(array, dtype=np.float32)\n",
+    "        return img\n",
+    "    \n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = 'C:/Users/snytk/Lerning_NN_for_work/datasets/2.4_learning'\n",
+    "path_to_pictures = 'C:/Users/snytk/Lerning_NN_for_work/datasets_jpg/2.4_jpg_learning'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  2%|█▍                                                                           | 158/8751 [01:06<1:01:14,  2.34it/s]"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.jpg' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.jpg' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.jpg'\n",
+    "        if not os.path.exists(savepath_real_png):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, resize = size)\n",
+    "            gc.collect()\n",
+    "            \n",
+    "            try:\n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "871d7ab6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/ImageDatasetCreate_spec_imag_real_from_npy_to_jpg_915.ipynb

@@ -0,0 +1,236 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4fdb98fc-65bb-467e-be0c-168fee9b0fca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda:0\n",
+      "['Solarize_Light2', '_classic_test_patch', '_mpl-gallery', '_mpl-gallery-nogrid', 'bmh', 'classic', 'dark_background', 'fast', 'fivethirtyeight', 'ggplot', 'grayscale', 'seaborn-v0_8', 'seaborn-v0_8-bright', 'seaborn-v0_8-colorblind', 'seaborn-v0_8-dark', 'seaborn-v0_8-dark-palette', 'seaborn-v0_8-darkgrid', 'seaborn-v0_8-deep', 'seaborn-v0_8-muted', 'seaborn-v0_8-notebook', 'seaborn-v0_8-paper', 'seaborn-v0_8-pastel', 'seaborn-v0_8-poster', 'seaborn-v0_8-talk', 'seaborn-v0_8-ticks', 'seaborn-v0_8-white', 'seaborn-v0_8-whitegrid', 'tableau-colorblind10']\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.ExitStack at 0x27e4cbae550>"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import time\n",
+    "import io\n",
+    "import cv2\n",
+    "import copy\n",
+    "import os\n",
+    "from tqdm import tqdm\n",
+    "import torch.nn as nn\n",
+    "import torch\n",
+    "import torchvision\n",
+    "from torch.utils.data import Dataset\n",
+    "from torch import default_generator, randperm\n",
+    "from PIL import Image\n",
+    "#from torch._utils import _accumulate\n",
+    "import csv\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "from scipy import ndimage\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "print(device)\n",
+    "batch_size = 16\n",
+    "momentum=0.9\n",
+    "lr = 1e-3\n",
+    "import random\n",
+    "sub_sample = 0.5\n",
+    "import matplotlib\n",
+    "import gc\n",
+    "matplotlib.use('Agg')\n",
+    "import matplotlib as mpl\n",
+    "mpl.rcParams['agg.path.chunksize'] = 256*256\n",
+    "#plt.style.use('mplstyle')\n",
+    "plt.style.use('ggplot')\n",
+    "plt.grid(None)\n",
+    "plt.rcParams[\"axes.grid\"] = False\n",
+    "print(plt.style.available)\n",
+    "plt.ioff()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9267fbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sig2pic_with_spec(path_to_data, filename, figsize=(16,16), dpi=16, resize = None):\n",
+    "    try:\n",
+    "        array = np.load(path_to_data+filename)\n",
+    "\n",
+    "        if resize != None:\n",
+    "            resized_real = cv2.resize(array[0], resize)\n",
+    "            resized_mag = cv2.resize(array[1], resize)\n",
+    "            resized_spectr = cv2.resize(array[2], resize)\n",
+    "            img = np.asarray(array, dtype=np.float32)\n",
+    "            return img\n",
+    "        \n",
+    "        img = np.asarray(array, dtype=np.float32)\n",
+    "        return img\n",
+    "    \n",
+    "    except Exception as e:\n",
+    "        print(str(e))\n",
+    "        return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "448da74a-e0ae-44d8-9877-8dd1f257a24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_to_binaries = 'C:/Users/snytk/Lerning_NN_for_work/datasets/915_learning'\n",
+    "path_to_pictures = 'C:/Users/snytk/Lerning_NN_for_work/datasets_jpg/915_jpg_learning'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ac4945a8-29c4-4da4-945f-08658953e3e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6f226f86-5d72-4573-8af6-750128b70263",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 856/856 [10:50<00:00,  1.32it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  drone  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 627/627 [08:40<00:00,  1.20it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dir:  noise  finished!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "size = (256,256)\n",
+    "if not os.path.exists(path_to_pictures):\n",
+    "    os.mkdir(path_to_pictures)\n",
+    "for subdir in os.listdir(path_to_binaries):\n",
+    "    filepath = path_to_binaries + '/' + subdir + '/'\n",
+    "    if not os.path.exists(path_to_pictures +'/' + subdir):\n",
+    "        os.mkdir(path_to_pictures + '/' + subdir)\n",
+    "    files = os.listdir(filepath)\n",
+    "    for file in tqdm(files):\n",
+    "        savepath_real_png = path_to_pictures +'/' + subdir + '/' + file + '_real' + '.jpg' \n",
+    "        savepath_imag_png = path_to_pictures +'/' + subdir + '/' + file + '_imag' + '.jpg' \n",
+    "        savepath_spec_png = path_to_pictures +'/' + subdir + '/' + file + '_spec' + '.jpg'\n",
+    "        if not os.path.exists(savepath_real_png):\n",
+    "            img = sig2pic_with_spec(path_to_data=filepath, filename=file, resize = size)\n",
+    "            gc.collect()\n",
+    "            \n",
+    "            try:\n",
+    "                plt.imshow(img[0])\n",
+    "                plt.savefig(savepath_real_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "                plt.imshow(img[1])\n",
+    "                plt.savefig(savepath_imag_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "\n",
+    "                plt.imshow(img[2])\n",
+    "                plt.savefig(savepath_spec_png)\n",
+    "                plt.clf()\n",
+    "                plt.cla()\n",
+    "                plt.close()\n",
+    "                \n",
+    "            except Exception:\n",
+    "                continue\n",
+    "    print('Dir: ', subdir , ' finished!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "871d7ab6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e080bb07",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/Jetson_пароли.txt

@@ -0,0 +1,7 @@
+Для ящика на выставки:
+aleksandr@192.168.3.85 19751975
+aleksandr@192.168.3.86 19751975
+
+Для ящика на Липецк:
+aleksandr@192.168.3.85 19751975
+aleksandr@192.168.3.86 19751975

train_scripts/PTH_to_PT.ipynb

@@ -0,0 +1,55 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a89c0273",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import torchvision\n",
+    "\n",
+    "def convert_pth_to_pt(pth_path, pt_path, model_class):\n",
+    "    state_dict = torch.load(pth_path)\n",
+    "    model = model_class()\n",
+    "    model.load_state_dict(state_dict)\n",
+    "    torch.save(model, pt_path)\n",
+    "    print(f'Model saved to {pt_path}')\n",
+    "\n",
+    "class ModelClass(torch.nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(ModelClass, self).__init__()\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        pass\n",
+    "\n",
+    "pth_path = 'model.pth'\n",
+    "pt_path = 'model.pt'\n",
+    "\n",
+    "convert_pth_to_pt(pth_path, pt_path, ModelClass)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/Training_models.ipynb

@@ -0,0 +1,463 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "5a13ad6b-56c9-4381-b376-1765f6dd7553",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Импортирование библиотек"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7311cb4a-5bf3-4268-b431-43eea10e9ed6",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda\n"
+     ]
+    },
+    {
+     "ename": "error",
+     "evalue": "OpenCV(4.10.0) D:\\a\\opencv-python\\opencv-python\\opencv\\modules\\highgui\\src\\window.cpp:1295: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvDestroyAllWindows'\n",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31merror\u001b[0m                                     Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[1], line 37\u001b[0m\n\u001b[0;32m     35\u001b[0m \u001b[38;5;28mprint\u001b[39m(device)\n\u001b[0;32m     36\u001b[0m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mempty_cache()\n\u001b[1;32m---> 37\u001b[0m \u001b[43mcv2\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdestroyAllWindows\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     38\u001b[0m gc\u001b[38;5;241m.\u001b[39mcollect()\n",
+      "\u001b[1;31merror\u001b[0m: OpenCV(4.10.0) D:\\a\\opencv-python\\opencv-python\\opencv\\modules\\highgui\\src\\window.cpp:1295: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvDestroyAllWindows'\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "from torch import default_generator, randperm\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "import torchvision.transforms as transforms\n",
+    "from torchvision.io import read_image\n",
+    "from importlib import import_module\n",
+    "import matplotlib.pyplot as plt\n",
+    "from torchvision import models\n",
+    "import torch, torchvision\n",
+    "from pathlib import Path\n",
+    "from PIL import Image\n",
+    "import torch.nn as nn\n",
+    "from tqdm import tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib\n",
+    "import os, shutil\n",
+    "import mlconfig\n",
+    "import random\n",
+    "import shutil\n",
+    "import timeit\n",
+    "import copy\n",
+    "import time\n",
+    "import cv2\n",
+    "import csv\n",
+    "import sys\n",
+    "import io\n",
+    "import gc\n",
+    "\n",
+    "plt.rcParams[\"savefig.bbox\"] = 'tight'\n",
+    "torch.manual_seed(1)\n",
+    "#matplotlib.use('Agg')\n",
+    "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
+    "print(device)\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "384de097-82c6-41f5-bda9-b2f54bc99593",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Подготовка и обучение детектирование"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "46e4dc99-6994-4fee-a32e-f3983bd991bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prepare_and_learning_detection(num_classes, num_samples, path_dataset, model_name, config_name, model):\n",
+    "    num_samples_per_class = num_samples // num_classes\n",
+    "\n",
+    "    #----------Создаём папку для сохранения результатов обучения--------------\n",
+    "    \n",
+    "    ind = 1\n",
+    "    while True:\n",
+    "        if os.path.exists(\"models/\" + model_name + str(ind)):\n",
+    "            ind += 1\n",
+    "        else:\n",
+    "            os.mkdir(\"models/\" + model_name + str(ind))\n",
+    "            path_res = \"models/\" + model_name + str(ind) + '/'\n",
+    "            break\n",
+    "    \n",
+    "    #----------Создаём файл dataset.csv для обучения--------------\n",
+    "    \n",
+    "    pd_columns = ['file_name']\n",
+    "    df = pd.DataFrame(columns=pd_columns)\n",
+    "    \n",
+    "    subdirs = os.listdir(path_dataset)\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        num_samples_per_class = min(num_samples_per_class, len(files))\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        random.shuffle(files)\n",
+    "        files_to_process = files[:num_samples_per_class]\n",
+    "        for file in files_to_process:\n",
+    "            row = pd.DataFrame({pd_columns[0]: [str(path_dataset + subdir + '/' + file)]})\n",
+    "            df = pd.concat([df, row], ignore_index=True)\n",
+    "    \n",
+    "    df.to_csv(path_res + 'dataset.csv', index=False)\n",
+    "    \n",
+    "    #----------Импортируем параметры для обучения--------------\n",
+    "    \n",
+    "    def load_function(attr):\n",
+    "        module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "        return getattr(import_module(module_), func)\n",
+    "    \n",
+    "    config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "    \n",
+    "    #----------Создаём класс датасета--------------\n",
+    "    \n",
+    "    class MyDataset(Dataset):\n",
+    "        def __init__(self, path_dataset, csv_file):\n",
+    "            data=[]\n",
+    "            with open(path_dataset + csv_file, newline='') as csvfile:\n",
+    "                reader = csv.reader(csvfile, delimiter=' ', quotechar='|')\n",
+    "                for row in list(reader)[1:]:\n",
+    "                    row = str(row)\n",
+    "                    data.append(row[2: len(row)-2])\n",
+    "            self.sig_filenames = data\n",
+    "            self.path_dataset = path_dataset\n",
+    "    \n",
+    "        def __len__(self):\n",
+    "            return len(self.sig_filenames)\n",
+    "    \n",
+    "        def __getitem__(self, idx):\n",
+    "            data_file = np.asarray(np.load(self.sig_filenames[idx], 'r+'), dtype=np.float32)\n",
+    "            if 'drone' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(0)\n",
+    "            if 'noise' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(1)\n",
+    "            return data_file, label\n",
+    "    \n",
+    "    #----------Создаём датасет--------------\n",
+    "    \n",
+    "    dataset = MyDataset(path_dataset=path_res, csv_file='dataset.csv')\n",
+    "    train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n",
+    "    batch_size = config.batch_size\n",
+    "    train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    valid_dataloader = torch.utils.data.DataLoader(valid_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    \n",
+    "    dataloaders = {}\n",
+    "    dataloaders['train'] = train_dataloader\n",
+    "    dataloaders['val'] = valid_dataloader\n",
+    "    dataset_sizes = {}\n",
+    "    dataset_sizes['train'] = len(train_set)\n",
+    "    dataset_sizes['val'] = len(valid_set)\n",
+    "\n",
+    "    #----------Обучаем модель--------------\n",
+    "\n",
+    "    val_loss = []\n",
+    "    val_acc = []\n",
+    "    train_loss = []\n",
+    "    train_acc = []\n",
+    "    epochs = config.epoch\n",
+    "    \n",
+    "    best_acc = 0.0\n",
+    "    best_model = copy.deepcopy(model.state_dict())\n",
+    "    limit = config.limit\n",
+    "    epoch_limit = epochs\n",
+    "    \n",
+    "    start = timeit.default_timer()\n",
+    "    for epoch in range(1, epochs+1):\n",
+    "        print(f\"Epoch : {epoch}\\n\")\n",
+    "        dataloader = None\n",
+    "    \n",
+    "        for phase in ['train', 'val']:\n",
+    "            running_loss = 0.0\n",
+    "            running_corrects = 0\n",
+    "    \n",
+    "            for (img, label) in tqdm(dataloaders[phase]):\n",
+    "                img, label = img.to(device), label.to(device)\n",
+    "                optimizer.zero_grad()\n",
+    "    \n",
+    "                with torch.set_grad_enabled(phase == 'train'):\n",
+    "                    output = model(img)\n",
+    "                    _, pred = torch.max(output.data, 1)\n",
+    "                    loss = criterion(output, label)\n",
+    "                    if phase=='train' :\n",
+    "                        loss.backward()\n",
+    "                        optimizer.step()\n",
+    "                \n",
+    "                running_loss += loss.item() * img.size(0)\n",
+    "                running_corrects += torch.sum(pred == label.data)\n",
+    "    \n",
+    "            epoch_loss = running_loss / dataset_sizes[phase]\n",
+    "            epoch_acc = running_corrects.double() / dataset_sizes[phase]\n",
+    "                \n",
+    "            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n",
+    "                    \n",
+    "            if phase=='train' :\n",
+    "                train_loss.append(epoch_loss)\n",
+    "                train_acc.append(epoch_acc)\n",
+    "            else :\n",
+    "                val_loss.append(epoch_loss)\n",
+    "                val_acc.append(epoch_acc)\n",
+    "                if val_acc[-1] > best_acc :\n",
+    "                    ind_limit = 0\n",
+    "                    best_acc = val_acc[-1]\n",
+    "                    best_model = copy.deepcopy(model.state_dict())\n",
+    "                    torch.save(best_model, path_res + model_name + '.pth')\n",
+    "                else:\n",
+    "                    ind_limit += 1\n",
+    "                    \n",
+    "                if ind_limit >= limit:\n",
+    "                    break\n",
+    "                \n",
+    "        if ind_limit >= limit:\n",
+    "            epoch_limit = epoch\n",
+    "            break\n",
+    "            \n",
+    "        print()\n",
+    "    \n",
+    "    end = timeit.default_timer()\n",
+    "    print(f\"Total time elapsed = {end - start} seconds\")\n",
+    "    epoch_limit += 1\n",
+    "    \n",
+    "    #----------Вывод графиков и сохранение результатов обучения--------------\n",
+    "    \n",
+    "    train_acc = np.asarray(list(map(lambda x: x.item(), train_acc)))\n",
+    "    val_acc = np.asarray(list(map(lambda x: x.item(), val_acc)))\n",
+    "    \n",
+    "    np.save(path_res+'train_acc.npy', train_acc)\n",
+    "    np.save(path_res+'val_acc.npy', val_acc)\n",
+    "    np.save(path_res+'train_loss.npy', train_loss)\n",
+    "    np.save(path_res+'val_loss.npy', val_loss)\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_loss, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_loss, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Loss')\n",
+    "    plt.title('Loss Curve')\n",
+    "    plt.legend(['Train Loss', 'Validation Loss'])\n",
+    "    plt.show()\n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_acc, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_acc, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Accuracy')\n",
+    "    plt.title('Accuracy Curve')\n",
+    "    plt.legend(['Train Accuracy', 'Validation Accuracy'])\n",
+    "    plt.show()\n",
+    "    \n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    torch.cuda.empty_cache()\n",
+    "    cv2.destroyAllWindows()\n",
+    "    del model\n",
+    "    gc.collect()\n",
+    "\n",
+    "    return path_res, model_name"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93c136ee",
+   "metadata": {},
+   "source": [
+    "### Ensemble"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "52e8d4c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.\n",
+      "  warnings.warn(msg)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch : 1\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 437/437 [23:49<00:00,  3.27s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "train Loss: 0.0884 Acc: 0.9634\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 187/187 [09:15<00:00,  2.97s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "val Loss: 0.0342 Acc: 0.9873\n",
+      "\n",
+      "Epoch : 2\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 84%|██████████████████████████████████████████████████████████████████▊             | 365/437 [19:28<04:18,  3.59s/it]"
+     ]
+    }
+   ],
+   "source": [
+    "#----------Инициализируем модель и параметры обучения--------------\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()\n",
+    "\n",
+    "num_classes = 3\n",
+    "config_name = \"ensemble\"\n",
+    "    \n",
+    "def load_function(attr):\n",
+    "    module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "    return getattr(import_module(module_), func)\n",
+    "    \n",
+    "config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "\n",
+    "model1 = models.resnet18(pretrained=False)\n",
+    "model2 = models.resnet50(pretrained=False)\n",
+    "model3 = models.resnet101(pretrained=False)\n",
+    "\n",
+    "num_classes = 2\n",
+    "\n",
+    "model1.fc = nn.Linear(model1.fc.in_features, num_classes)\n",
+    "model2.fc = nn.Linear(model2.fc.in_features, num_classes)\n",
+    "model3.fc = nn.Linear(model3.fc.in_features, num_classes)\n",
+    "\n",
+    "class Ensemble(nn.Module):\n",
+    "    def __init__(self, model1, model2, model3):\n",
+    "        super(Ensemble, self).__init__()\n",
+    "        self.model1 = model1\n",
+    "        self.model2 = model2\n",
+    "        self.model3 = model3\n",
+    "        self.fc = nn.Linear(3 * num_classes, num_classes)\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x1 = self.model1(x)\n",
+    "        x2 = self.model2(x)\n",
+    "        x3 = self.model3(x)\n",
+    "        x = torch.cat((x1, x2, x3), dim=1)\n",
+    "        x = self.fc(x)\n",
+    "        return x\n",
+    "\n",
+    "model = Ensemble(model1, model2, model3)\n",
+    "\n",
+    "optimizer = load_function(config.optimizer.name)(model.parameters(), lr=config.optimizer.lr)\n",
+    "criterion = load_function(config.loss_function.name)()\n",
+    "scheduler = load_function(config.scheduler.name)(optimizer, step_size=config.scheduler.step_size, gamma=config.scheduler.gamma)\n",
+    "\n",
+    "if device != 'cpu':\n",
+    "    model = model.to(device)\n",
+    "\n",
+    "#----------Создания датасета и обучение модели--------------\n",
+    "\n",
+    "path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 10000, path_dataset = \"//192.168.1.64/data/DATASETS/2.4/2.4_learning/\", \n",
+    "                     model_name = config_name+\"_2.4_\", config_name = config_name, model=model)\n",
+    "\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "del model\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "57d18676",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "celltoolbar": "Отсутствует",
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/Training_models2pic_val_loss.ipynb

@@ -0,0 +1,523 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e1db882b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/sibscience-4/from_ssh/DroneDetector/.venv-train/lib/python3.12/site-packages/matplotlib/projections/__init__.py:63: UserWarning: Unable to import Axes3D. This may be due to multiple versions of Matplotlib being installed (e.g. as a system package and as a pip package). As a result, the 3D projection is not available.\n",
+      "  warnings.warn(\"Unable to import Axes3D. This may be due to multiple versions of \"\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "220"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "from torch import default_generator, randperm\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "import torchvision.transforms as transforms\n",
+    "from torchvision.io import read_image\n",
+    "from importlib import import_module\n",
+    "import matplotlib.pyplot as plt\n",
+    "from torchvision import models\n",
+    "import torch, torchvision\n",
+    "from pathlib import Path\n",
+    "from PIL import Image\n",
+    "import torch.nn as nn\n",
+    "from tqdm import tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib\n",
+    "import os, shutil\n",
+    "import mlconfig\n",
+    "import random\n",
+    "import shutil\n",
+    "import timeit\n",
+    "import copy\n",
+    "import time\n",
+    "import cv2\n",
+    "import csv\n",
+    "import sys\n",
+    "import io\n",
+    "import gc\n",
+    "\n",
+    "plt.rcParams[\"savefig.bbox\"] = 'tight'\n",
+    "torch.manual_seed(1)\n",
+    "#matplotlib.use('Agg')\n",
+    "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
+    "print(device)\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8e009995",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prepare_and_learning_detection(num_classes, num_samples, path_dataset, model_name, config_name, model,selected_freq):\n",
+    "    num_samples_per_class = num_samples // num_classes\n",
+    "\n",
+    "    #----------Создаём папку для сохранения результатов обучения--------------\n",
+    "    os.makedirs(\"models\", exist_ok=True)\n",
+    "    ind = 1\n",
+    "    while True:\n",
+    "        if os.path.exists(\"models/\" + model_name + str(ind)):\n",
+    "            ind += 1\n",
+    "        else:\n",
+    "            os.mkdir(\"models/\" + model_name + str(ind))\n",
+    "            path_res = \"models/\" + model_name + str(ind) + '/'\n",
+    "            break\n",
+    "    \n",
+    "    #----------Создаём файл dataset.csv для обучения--------------\n",
+    "    \n",
+    "    pd_columns = ['file_name']\n",
+    "    df = pd.DataFrame(columns=pd_columns)\n",
+    "    \n",
+    "    subdirs = os.listdir(path_dataset)\n",
+    "    \n",
+    "    for subdir in subdirs:\n",
+    "        freq_dir = os.path.join(path_dataset, subdir, str(selected_freq)+\"_jpg\")\n",
+    "        if not os.path.isdir(freq_dir):\n",
+    "            print(\"Error1\")\n",
+    "            continue\n",
+    "        \n",
+    "        files_k=[f for f in os.listdir(freq_dir)]\n",
+    "        print(len(files_k))\n",
+    "        \n",
+    "        files = [\n",
+    "                f for f in os.listdir(freq_dir)\n",
+    "                if os.path.isfile(os.path.join(freq_dir, f)) and f.endswith('imag.png')\n",
+    "            ]\n",
+    "        num_samples_per_class = min(num_samples_per_class, len(files))\n",
+    "        print(f\"num_samples per class {subdir} is {num_samples_per_class}\")\n",
+    "\n",
+    "    for subdir in subdirs:\n",
+    "        freq_dir = os.path.join(path_dataset, subdir, str(selected_freq)+\"_jpg\")\n",
+    "        if not os.path.isdir(freq_dir):\n",
+    "            print(\"Error1\")\n",
+    "            continue\n",
+    "\n",
+    "        files = [\n",
+    "            f for f in os.listdir(freq_dir)\n",
+    "            if os.path.isfile(os.path.join(freq_dir, f)) and f.endswith('imag.png')\n",
+    "        ]\n",
+    "        random.shuffle(files)\n",
+    "        files_to_process = files[:num_samples_per_class]\n",
+    "\n",
+    "        for file in files_to_process:\n",
+    "            row = pd.DataFrame({\n",
+    "                pd_columns[0]: [str(os.path.join(freq_dir, file))]\n",
+    "            })\n",
+    "            df = pd.concat([df, row], ignore_index=True)\n",
+    "\n",
+    "    dataset_csv_path = os.path.join(path_res, 'dataset.csv')\n",
+    "    df.to_csv(dataset_csv_path, index=False)\n",
+    "\n",
+    "    if not os.path.exists(dataset_csv_path):\n",
+    "        raise RuntimeError(f'dataset.csv was not created: {dataset_csv_path}')\n",
+    "    #----------Импортируем параметры для обучения--------------\n",
+    "    \n",
+    "    def load_function(attr):\n",
+    "        module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "        return getattr(import_module(module_), func)\n",
+    "    \n",
+    "    config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "    \n",
+    "    #----------Создаём класс датасета--------------\n",
+    "    \n",
+    "    class MyDataset(Dataset):\n",
+    "        def __init__(self, path_dataset, csv_file):\n",
+    "            data=[]\n",
+    "            with open(os.path.join(path_dataset, csv_file), newline='') as csvfile:\n",
+    "                reader = csv.reader(csvfile, delimiter=' ', quotechar='|')\n",
+    "                for row in list(reader)[1:]:\n",
+    "                    row = str(row)\n",
+    "                    data.append(row[2: len(row)-2])\n",
+    "            self.path_dataset = path_dataset\n",
+    "            self.target_shape = None\n",
+    "            self.target_hw = None\n",
+    "            self.sig_filenames = self._validate_files(data)\n",
+    "\n",
+    "        def _pair_paths(self, filename):\n",
+    "            base = os.path.splitext(filename)[0]\n",
+    "            if base.endswith(\"real\"):\n",
+    "                return base + \".png\", base[:-4] + \"imag.png\"\n",
+    "            if base.endswith(\"imag\"):\n",
+    "                return base[:-4] + \"real.png\", base + \".png\"\n",
+    "            return None, None\n",
+    "\n",
+    "        @staticmethod\n",
+    "        def _read_shape(path):\n",
+    "            img = cv2.imread(path)\n",
+    "            if img is None:\n",
+    "                return None\n",
+    "            return img.shape\n",
+    "\n",
+    "        def _validate_files(self, filenames):\n",
+    "            from collections import Counter\n",
+    "\n",
+    "            candidates = []\n",
+    "            dropped = []\n",
+    "            shape_counter = Counter()\n",
+    "\n",
+    "            for filename in filenames:\n",
+    "                real_path, imag_path = self._pair_paths(filename)\n",
+    "                if real_path is None or imag_path is None:\n",
+    "                    dropped.append((filename, \"bad file suffix\"))\n",
+    "                    continue\n",
+    "\n",
+    "                real_shape = self._read_shape(real_path)\n",
+    "                imag_shape = self._read_shape(imag_path)\n",
+    "                if real_shape is None or imag_shape is None:\n",
+    "                    dropped.append((filename, f\"read failed real={real_shape} imag={imag_shape}\"))\n",
+    "                    continue\n",
+    "                if real_shape != imag_shape:\n",
+    "                    dropped.append((filename, f\"pair shape mismatch real={real_shape} imag={imag_shape}\"))\n",
+    "                    continue\n",
+    "\n",
+    "                shape_counter[real_shape] += 1\n",
+    "                candidates.append((filename, real_shape))\n",
+    "\n",
+    "            if not candidates:\n",
+    "                raise RuntimeError(\"No valid image pairs left after shape validation\")\n",
+    "\n",
+    "            preferred_shape = (1600, 1600, 3)\n",
+    "            if shape_counter.get(preferred_shape, 0) > 0:\n",
+    "                target_shape = preferred_shape\n",
+    "            else:\n",
+    "                target_shape = shape_counter.most_common(1)[0][0]\n",
+    "\n",
+    "            self.target_shape = target_shape\n",
+    "            self.target_hw = target_shape[:2]\n",
+    "            valid = [filename for filename, _shape in candidates]\n",
+    "            resized_count = sum(1 for _filename, shape in candidates if shape != target_shape)\n",
+    "\n",
+    "            print(f\"[dataset-shape-filter] shape_distribution={dict(shape_counter)}\")\n",
+    "            print(\n",
+    "                f\"[dataset-shape-filter] target_shape={target_shape} \"\n",
+    "                f\"kept={len(valid)} dropped={len(dropped)} will_resize={resized_count}\"\n",
+    "            )\n",
+    "            for filename, reason in dropped[:20]:\n",
+    "                print(f\"[dataset-shape-filter] drop {filename}: {reason}\")\n",
+    "            if len(dropped) > 20:\n",
+    "                print(f\"[dataset-shape-filter] ... {len(dropped) - 20} more dropped\")\n",
+    "\n",
+    "            return valid\n",
+    "\n",
+    "        def __len__(self):\n",
+    "            return len(self.sig_filenames)\n",
+    "\n",
+    "        def _read_image_chw(self, path):\n",
+    "            img = cv2.imread(path)\n",
+    "            if img is None:\n",
+    "                raise RuntimeError(f\"failed to read image: {path}\")\n",
+    "            if img.shape[:2] != self.target_hw:\n",
+    "                img = cv2.resize(\n",
+    "                    img,\n",
+    "                    (self.target_hw[1], self.target_hw[0]),\n",
+    "                    interpolation=cv2.INTER_AREA,\n",
+    "                )\n",
+    "            return np.asarray(cv2.split(img), dtype=np.float32)\n",
+    "\n",
+    "        def __getitem__(self, idx):\n",
+    "            real_path, imag_path = self._pair_paths(self.sig_filenames[idx])\n",
+    "            image_real = self._read_image_chw(real_path)\n",
+    "            image_imag = self._read_image_chw(imag_path)\n",
+    "\n",
+    "            path_parts = set(self.sig_filenames[idx].split('/'))\n",
+    "            if 'drone' in path_parts:\n",
+    "                label = torch.tensor(0)\n",
+    "            elif 'noise' in path_parts:\n",
+    "                label = torch.tensor(1)\n",
+    "            else:\n",
+    "                raise RuntimeError(f\"cannot infer label from path: {self.sig_filenames[idx]}\")\n",
+    "\n",
+    "            return image_real, image_imag, label\n",
+    "\n",
+    "    #----------Создаём датасет--------------\n",
+    "    \n",
+    "    dataset = MyDataset(path_dataset=path_res, csv_file='dataset.csv')\n",
+    "    train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n",
+    "    batch_size = config.batch_size\n",
+    "    train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    valid_dataloader = torch.utils.data.DataLoader(valid_set, batch_size=batch_size, shuffle=False, drop_last=False)\n",
+    "    \n",
+    "    dataloaders = {}\n",
+    "    dataloaders['train'] = train_dataloader\n",
+    "    dataloaders['val'] = valid_dataloader\n",
+    "    dataset_sizes = {}\n",
+    "    dataset_sizes['train'] = len(train_set)\n",
+    "    dataset_sizes['val'] = len(valid_set)\n",
+    "\n",
+    "    #----------Обучаем модель--------------\n",
+    "\n",
+    "    val_loss = []\n",
+    "    val_acc = []\n",
+    "    train_loss = []\n",
+    "    train_acc = []\n",
+    "    epochs = config.epoch\n",
+    "    min_delta = 1e-4\n",
+    "    \n",
+    "    best_val_loss = float('inf')\n",
+    "    best_model = copy.deepcopy(model.state_dict())\n",
+    "    limit = config.limit\n",
+    "    ind_limit = 0\n",
+    "    epoch_limit = epochs\n",
+    "    \n",
+    "    start = timeit.default_timer()\n",
+    "    for epoch in range(1, epochs+1):\n",
+    "        print(f\"Epoch : {epoch}\\n\")\n",
+    "        \n",
+    "        for phase in ['train', 'val']:\n",
+    "            if phase == 'train':\n",
+    "                model.train()\n",
+    "            else:\n",
+    "                model.eval()\n",
+    "\n",
+    "            running_loss = 0.0\n",
+    "            running_corrects = 0\n",
+    "    \n",
+    "            for (img1, img2, label) in tqdm(dataloaders[phase]):\n",
+    "                img1, img2, label = img1.to(device), img2.to(device), label.to(device)\n",
+    "                optimizer.zero_grad()\n",
+    "    \n",
+    "                with torch.set_grad_enabled(phase == 'train'):\n",
+    "                    output = model([img1, img2])\n",
+    "                    _, pred = torch.max(output.data, 1)\n",
+    "                    loss = criterion(output, label)\n",
+    "                    if phase == 'train':\n",
+    "                        loss.backward()\n",
+    "                        optimizer.step()\n",
+    "                \n",
+    "                running_loss += loss.item() * img1.size(0)\n",
+    "                running_corrects += torch.sum(pred == label.data)\n",
+    "    \n",
+    "            epoch_loss = running_loss / dataset_sizes[phase]\n",
+    "            epoch_acc = running_corrects.double() / dataset_sizes[phase]\n",
+    "                \n",
+    "            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n",
+    "                    \n",
+    "            if phase == 'train':\n",
+    "                train_loss.append(epoch_loss)\n",
+    "                train_acc.append(epoch_acc)\n",
+    "            else:\n",
+    "                val_loss.append(epoch_loss)\n",
+    "                val_acc.append(epoch_acc)\n",
+    "                scheduler.step(epoch_loss)\n",
+    "\n",
+    "                current_lr = optimizer.param_groups[0]['lr']\n",
+    "                print(f'val lr: {current_lr:.8f}')\n",
+    "\n",
+    "                if epoch_loss < (best_val_loss - min_delta):\n",
+    "                    ind_limit = 0\n",
+    "                    best_val_loss = epoch_loss\n",
+    "                    best_model = copy.deepcopy(model.state_dict())\n",
+    "                    torch.save(best_model, path_res + model_name + '.pth')\n",
+    "                    print(f'saved best model with val_loss={best_val_loss:.4f}')\n",
+    "                else:\n",
+    "                    ind_limit += 1\n",
+    "                    print(f'early stopping patience: {ind_limit}/{limit}')\n",
+    "                    \n",
+    "                if ind_limit >= limit:\n",
+    "                    break\n",
+    "                \n",
+    "        if ind_limit >= limit:\n",
+    "            epoch_limit = epoch\n",
+    "            break\n",
+    "            \n",
+    "        print()\n",
+    "    \n",
+    "    end = timeit.default_timer()\n",
+    "    print(f\"Total time elapsed = {end - start} seconds\")\n",
+    "    epoch_limit += 1\n",
+    "    \n",
+    "    #----------Вывод графиков и сохранение результатов обучения--------------\n",
+    "    \n",
+    "    train_acc = np.asarray(list(map(lambda x: x.item(), train_acc)))\n",
+    "    val_acc = np.asarray(list(map(lambda x: x.item(), val_acc)))\n",
+    "    \n",
+    "    np.save(path_res+'train_acc.npy', train_acc)\n",
+    "    np.save(path_res+'val_acc.npy', val_acc)\n",
+    "    np.save(path_res+'train_loss.npy', train_loss)\n",
+    "    np.save(path_res+'val_loss.npy', val_loss)\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_loss, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_loss, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Loss')  \n",
+    "             \n",
+    "    plt.title('Loss Curve')\n",
+    "    plt.legend(['Train Loss', 'Validation Loss'])\n",
+    "    plt.show()\n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_acc, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_acc, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Accuracy')\n",
+    "    plt.title('Accuracy Curve')\n",
+    "    plt.legend(['Train Accuracy', 'Validation Accuracy'])\n",
+    "    plt.show()\n",
+    "    \n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    torch.cuda.empty_cache()\n",
+    "    cv2.destroyAllWindows()\n",
+    "    del model\n",
+    "    gc.collect()\n",
+    "\n",
+    "    return path_res, model_name"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bbbe7fea",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/sibscience-4/from_ssh/DroneDetector/.venv-train/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
+      "  warnings.warn(\n",
+      "/home/sibscience-4/from_ssh/DroneDetector/.venv-train/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.\n",
+      "  warnings.warn(msg)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Error1\n",
+      "Error1\n",
+      "Error1\n",
+      "Error1\n",
+      "Error1\n",
+      "Error1\n"
+     ]
+    },
+    {
+     "ename": "RuntimeError",
+     "evalue": "No valid image pairs left after shape validation",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mRuntimeError\u001b[39m                              Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[4]\u001b[39m\u001b[32m, line 45\u001b[39m\n\u001b[32m     41\u001b[39m     model = model.to(device)\n\u001b[32m     42\u001b[39m \n\u001b[32m     43\u001b[39m \u001b[38;5;66;03m#----------Создания датасета и обучение модели--------------\u001b[39;00m\n\u001b[32m     44\u001b[39m \n\u001b[32m---> \u001b[39m\u001b[32m45\u001b[39m path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 10000, path_dataset = \"/mnt/data/Dataset_overlay\", \n\u001b[32m     46\u001b[39m                      selected_freq=\u001b[32m1200\u001b[39m,model_name = config_name+\u001b[33m\"1200_\"\u001b[39m, config_name = config_name, model=model)\n\u001b[32m     47\u001b[39m \n\u001b[32m     48\u001b[39m \n",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 183\u001b[39m, in \u001b[36mprepare_and_learning_detection\u001b[39m\u001b[34m(num_classes, num_samples, path_dataset, model_name, config_name, model, selected_freq)\u001b[39m\n\u001b[32m    179\u001b[39m             \u001b[38;5;28;01mreturn\u001b[39;00m image_real, image_imag, label\n\u001b[32m    180\u001b[39m \n\u001b[32m    181\u001b[39m     \u001b[38;5;66;03m#----------Создаём датасет--------------\u001b[39;00m\n\u001b[32m    182\u001b[39m \n\u001b[32m--> \u001b[39m\u001b[32m183\u001b[39m     dataset = MyDataset(path_dataset=path_res, csv_file=\u001b[33m'dataset.csv'\u001b[39m)\n\u001b[32m    184\u001b[39m     train_set, valid_set = torch.utils.data.random_split(dataset, [\u001b[32m0.7\u001b[39m, \u001b[32m0.3\u001b[39m], generator=torch.Generator().manual_seed(\u001b[32m42\u001b[39m))\n\u001b[32m    185\u001b[39m     batch_size = config.batch_size\n\u001b[32m    186\u001b[39m     train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=\u001b[38;5;28;01mTrue\u001b[39;00m, drop_last=\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 83\u001b[39m, in \u001b[36mprepare_and_learning_detection.<locals>.MyDataset.__init__\u001b[39m\u001b[34m(self, path_dataset, csv_file)\u001b[39m\n\u001b[32m     79\u001b[39m                     data.append(row[\u001b[32m2\u001b[39m: len(row)-\u001b[32m2\u001b[39m])\n\u001b[32m     80\u001b[39m             self.path_dataset = path_dataset\n\u001b[32m     81\u001b[39m             self.target_shape = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m     82\u001b[39m             self.target_hw = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m83\u001b[39m             self.sig_filenames = self._validate_files(data)\n",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 126\u001b[39m, in \u001b[36mprepare_and_learning_detection.<locals>.MyDataset._validate_files\u001b[39m\u001b[34m(self, filenames)\u001b[39m\n\u001b[32m    122\u001b[39m                 shape_counter[real_shape] += \u001b[32m1\u001b[39m\n\u001b[32m    123\u001b[39m                 candidates.append((filename, real_shape))\n\u001b[32m    124\u001b[39m \n\u001b[32m    125\u001b[39m             \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28;01mnot\u001b[39;00m candidates:\n\u001b[32m--> \u001b[39m\u001b[32m126\u001b[39m                 \u001b[38;5;28;01mraise\u001b[39;00m RuntimeError(\u001b[33m\"No valid image pairs left after shape validation\"\u001b[39m)\n\u001b[32m    127\u001b[39m \n\u001b[32m    128\u001b[39m             preferred_shape = (\u001b[32m1600\u001b[39m, \u001b[32m1600\u001b[39m, \u001b[32m3\u001b[39m)\n\u001b[32m    129\u001b[39m             \u001b[38;5;28;01mif\u001b[39;00m shape_counter.get(preferred_shape, \u001b[32m0\u001b[39m) > \u001b[32m0\u001b[39m:\n",
+      "\u001b[31mRuntimeError\u001b[39m: No valid image pairs left after shape validation"
+     ]
+    }
+   ],
+   "source": [
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()\n",
+    "\n",
+    "config_name = \"ensemble\"\n",
+    "    \n",
+    "def load_function(attr):\n",
+    "    module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "    return getattr(import_module(module_), func)\n",
+    "    \n",
+    "config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "\n",
+    "model1 = models.resnet18(pretrained=False)\n",
+    "model2 = models.resnet50(pretrained=False)\n",
+    "\n",
+    "num_classes = 2\n",
+    "\n",
+    "model1.fc = nn.Linear(model1.fc.in_features, num_classes)\n",
+    "model2.fc = nn.Linear(model2.fc.in_features, num_classes)\n",
+    "\n",
+    "class Ensemble(nn.Module):\n",
+    "    def __init__(self, model1, model2):\n",
+    "        super(Ensemble, self).__init__()\n",
+    "        self.model1 = model1\n",
+    "        self.model2 = model2\n",
+    "        self.fc = nn.Linear(2 * num_classes, num_classes)\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x1 = self.model1(x[0])\n",
+    "        x2 = self.model2(x[1])\n",
+    "        x = torch.cat((x1, x2), dim=1)\n",
+    "        x = self.fc(x)\n",
+    "        return x\n",
+    "model = Ensemble(model1, model2)\n",
+    "\n",
+    "optimizer = load_function(config.optimizer.name)(model.parameters(), lr=config.optimizer.lr)\n",
+    "criterion = load_function(config.loss_function.name)()\n",
+    "scheduler = load_function(config.scheduler.name)(optimizer, step_size=config.scheduler.step_size, gamma=config.scheduler.gamma)\n",
+    "\n",
+    "if device != 'cpu':\n",
+    "    model = model.to(device)\n",
+    "\n",
+    "#----------Создания датасета и обучение модели--------------\n",
+    "\n",
+    "path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 10000, path_dataset = \"/mnt/data/Dataset_overlay\", \n",
+    "                     selected_freq=2400,model_name = config_name+\"2400_\", config_name = config_name, model=model)\n",
+    "\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "del model\n",
+    "gc.collect()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "usr",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/Training_models_1.2.ipynb

@@ -15,7 +15,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "7311cb4a-5bf3-4268-b431-43eea10e9ed6",
    "metadata": {
     "slideshow": {
@@ -24,6 +24,14 @@
     "tags": []
    },
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/sibscience-4/from_ssh/DroneDetector/.venv-train/lib/python3.12/site-packages/matplotlib/projections/__init__.py:63: UserWarning: Unable to import Axes3D. This may be due to multiple versions of Matplotlib being installed (e.g. as a system package and as a pip package). As a result, the 3D projection is not available.\n",
+      "  warnings.warn(\"Unable to import Axes3D. This may be due to multiple versions of \"\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -34,10 +42,10 @@
     {
      "data": {
       "text/plain": [
-       "88"
+       "191"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -106,6 +114,7 @@
     "def prepare_and_learning_detection(num_classes, num_samples, path_dataset, model_name, config_name, model,selected_freq):\n",
     "    num_samples_per_class = num_samples // num_classes\n",
     "\n",
+    "\n",
     "    #----------Создаём папку для сохранения результатов обучения--------------\n",
     "    os.makedirs(\"models\", exist_ok=True)\n",
     "    ind = 1\n",
@@ -124,11 +133,9 @@
     "    \n",
     "    subdirs = os.listdir(path_dataset)\n",
     "    print(subdirs)\n",
-    "    print(\"huy\")\n",
     "    \n",
     "    for subdir in subdirs:\n",
-    "        freq_dir = os.path.join(path_dataset, subdir, str(str(selected_freq))+\"_jpg\")\n",
-    "        print(freq_dir)\n",
+    "        freq_dir = os.path.join(path_dataset, subdir, str(selected_freq))\n",
     "        if not os.path.isdir(freq_dir):\n",
     "            continue\n",
     "\n",
@@ -139,8 +146,7 @@
     "        num_samples_per_class = min(num_samples_per_class, len(files))\n",
     "\n",
     "    for subdir in subdirs:\n",
-    "        freq_dir = os.path.join(path_dataset, subdir,str(str(selected_freq))+\"_jpg\")\n",
-    "        print(freq_dir)\n",
+    "        freq_dir = os.path.join(path_dataset, subdir, str(selected_freq))\n",
     "        if not os.path.isdir(freq_dir):\n",
     "            continue\n",
     "\n",
@@ -180,6 +186,7 @@
     "                for row in list(reader)[1:]:\n",
     "                    row = str(row)\n",
     "                    data.append(row[2: len(row)-2])\n",
+    "\n",
     "            self.sig_filenames = data\n",
     "            self.path_dataset = path_dataset\n",
     "    \n",
@@ -189,6 +196,9 @@
     "        def __getitem__(self, idx):\n",
     "            base = os.path.splitext(self.sig_filenames[idx])[0]\n",
     "\n",
+    "            #raise(base)\n",
+    "\n",
+    "            exit(1)\n",
     "            image_real = np.asarray(cv2.split(cv2.imread(base + '_real.png')), dtype=np.float32)\n",
     "            image_imag = np.asarray(cv2.split(cv2.imread(base + '_imag.png')), dtype=np.float32)\n",
     "            image_spec = np.asarray(cv2.split(cv2.imread(base + '_spec.png')), dtype=np.float32)\n",
@@ -196,11 +206,12 @@
     "            if 'drone' in list(self.sig_filenames[idx].split('/')):\n",
     "                label = torch.tensor(0)\n",
     "            if 'noise' in list(self.sig_filenames[idx].split('/')):\n",
+    "                exit(1)\n",
     "                label = torch.tensor(1)\n",
     "            return image_real, image_imag, image_spec, label\n",
     "    \n",
     "    #----------Создаём датасет--------------\n",
-    "    \n",
+    "    exit(1)\n",
     "    dataset = MyDataset(path_dataset=path_res, csv_file='dataset.csv')\n",
     "    train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n",
     "    batch_size = config.batch_size\n",
@@ -335,39 +346,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 13,
    "id": "52e8d4c5",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/sibsci/DroneDetector/.venv-train/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
-      "  warnings.warn(\n",
-      "/home/sibsci/DroneDetector/.venv-train/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.\n",
-      "  warnings.warn(msg)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "['noise', 'drone']\n",
-      "huy\n",
-      "/home/sibsci/dataset_img/noise/5800_jpg\n",
-      "/home/sibsci/dataset_img/drone/5800_jpg\n",
-      "/home/sibsci/dataset_img/noise/5800/_jpg\n",
-      "/home/sibsci/dataset_img/drone/5800/_jpg\n"
+      "['noise', 'drone']\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_84402/382832652.py:100: UserWarning: Length of split at index 0 is 0. This might result in an empty dataset.\n",
+      "/tmp/ipykernel_3754538/2835334388.py:103: UserWarning: Length of split at index 0 is 0. This might result in an empty dataset.\n",
       "  train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n",
-      "/tmp/ipykernel_84402/382832652.py:100: UserWarning: Length of split at index 1 is 0. This might result in an empty dataset.\n",
+      "/tmp/ipykernel_3754538/2835334388.py:103: UserWarning: Length of split at index 1 is 0. This might result in an empty dataset.\n",
       "  train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n"
      ]
     },
@@ -378,10 +374,10 @@
      "traceback": [
       "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
       "\u001b[31mValueError\u001b[39m                                Traceback (most recent call last)",
-      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[9]\u001b[39m\u001b[32m, line 53\u001b[39m\n\u001b[32m     49\u001b[39m     model = model.to(device)\n\u001b[32m     50\u001b[39m \n\u001b[32m     51\u001b[39m \u001b[38;5;66;03m#----------Создания датасета и обучение модели--------------\u001b[39;00m\n\u001b[32m     52\u001b[39m \n\u001b[32m---> \u001b[39m\u001b[32m53\u001b[39m path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 1000, path_dataset = \"/home/sibsci/dataset_img\", \n\u001b[32m     54\u001b[39m                      selected_freq=\u001b[32m5800\u001b[39m,model_name = config_name+\u001b[33m\"_5.8_jpg_\"\u001b[39m, config_name = config_name, model=model)\n\u001b[32m     55\u001b[39m \n\u001b[32m     56\u001b[39m \n",
-      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[8]\u001b[39m\u001b[32m, line 102\u001b[39m, in \u001b[36mprepare_and_learning_detection\u001b[39m\u001b[34m(num_classes, num_samples, path_dataset, model_name, config_name, model, selected_freq)\u001b[39m\n\u001b[32m     98\u001b[39m \n\u001b[32m     99\u001b[39m     dataset = MyDataset(path_dataset=path_res, csv_file=\u001b[33m'dataset.csv'\u001b[39m)\n\u001b[32m    100\u001b[39m     train_set, valid_set = torch.utils.data.random_split(dataset, [\u001b[32m0.7\u001b[39m, \u001b[32m0.3\u001b[39m], generator=torch.Generator().manual_seed(\u001b[32m42\u001b[39m))\n\u001b[32m    101\u001b[39m     batch_size = config.batch_size\n\u001b[32m--> \u001b[39m\u001b[32m102\u001b[39m     train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=\u001b[38;5;28;01mTrue\u001b[39;00m, drop_last=\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[32m    103\u001b[39m     valid_dataloader = torch.utils.data.DataLoader(valid_set, batch_size=batch_size, shuffle=\u001b[38;5;28;01mTrue\u001b[39;00m, drop_last=\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[32m    104\u001b[39m \n\u001b[32m    105\u001b[39m     dataloaders = {}\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m~/DroneDetector/.venv-train/lib/python3.12/site-packages/torch/utils/data/dataloader.py:394\u001b[39m, in \u001b[36mDataLoader.__init__\u001b[39m\u001b[34m(self, dataset, batch_size, shuffle, sampler, batch_sampler, num_workers, collate_fn, pin_memory, drop_last, timeout, worker_init_fn, multiprocessing_context, generator, prefetch_factor, persistent_workers, pin_memory_device, in_order)\u001b[39m\n\u001b[32m    392\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:  \u001b[38;5;66;03m# map-style\u001b[39;00m\n\u001b[32m    393\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m shuffle:\n\u001b[32m--> \u001b[39m\u001b[32m394\u001b[39m         sampler = \u001b[43mRandomSampler\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdataset\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgenerator\u001b[49m\u001b[43m=\u001b[49m\u001b[43mgenerator\u001b[49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m    395\u001b[39m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m    396\u001b[39m         sampler = SequentialSampler(dataset)  \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m~/DroneDetector/.venv-train/lib/python3.12/site-packages/torch/utils/data/sampler.py:149\u001b[39m, in \u001b[36mRandomSampler.__init__\u001b[39m\u001b[34m(self, data_source, replacement, num_samples, generator)\u001b[39m\n\u001b[32m    144\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\n\u001b[32m    145\u001b[39m         \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mreplacement should be a boolean value, but got replacement=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.replacement\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m    146\u001b[39m     )\n\u001b[32m    148\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m.num_samples, \u001b[38;5;28mint\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m.num_samples <= \u001b[32m0\u001b[39m:\n\u001b[32m--> \u001b[39m\u001b[32m149\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m    150\u001b[39m         \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mnum_samples should be a positive integer value, but got num_samples=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.num_samples\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m    151\u001b[39m     )\n",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[13]\u001b[39m\u001b[32m, line 49\u001b[39m\n\u001b[32m     45\u001b[39m     model = model.to(device)\n\u001b[32m     46\u001b[39m \n\u001b[32m     47\u001b[39m \u001b[38;5;66;03m#----------Создания датасета и обучение модели--------------\u001b[39;00m\n\u001b[32m     48\u001b[39m \n\u001b[32m---> \u001b[39m\u001b[32m49\u001b[39m path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 10000, path_dataset = \"/mnt/data/Dataset_img\", \n\u001b[32m     50\u001b[39m                      selected_freq=\u001b[32m2400\u001b[39m,model_name = config_name+\u001b[33m\"_2.4_jpg_\"\u001b[39m, config_name = config_name, model=model)\n\u001b[32m     51\u001b[39m \n\u001b[32m     52\u001b[39m \n",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[12]\u001b[39m\u001b[32m, line 105\u001b[39m, in \u001b[36mprepare_and_learning_detection\u001b[39m\u001b[34m(num_classes, num_samples, path_dataset, model_name, config_name, model, selected_freq)\u001b[39m\n\u001b[32m    101\u001b[39m     exit(\u001b[32m1\u001b[39m)\n\u001b[32m    102\u001b[39m     dataset = MyDataset(path_dataset=path_res, csv_file=\u001b[33m'dataset.csv'\u001b[39m)\n\u001b[32m    103\u001b[39m     train_set, valid_set = torch.utils.data.random_split(dataset, [\u001b[32m0.7\u001b[39m, \u001b[32m0.3\u001b[39m], generator=torch.Generator().manual_seed(\u001b[32m42\u001b[39m))\n\u001b[32m    104\u001b[39m     batch_size = config.batch_size\n\u001b[32m--> \u001b[39m\u001b[32m105\u001b[39m     train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=\u001b[38;5;28;01mTrue\u001b[39;00m, drop_last=\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[32m    106\u001b[39m     valid_dataloader = torch.utils.data.DataLoader(valid_set, batch_size=batch_size, shuffle=\u001b[38;5;28;01mTrue\u001b[39;00m, drop_last=\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[32m    107\u001b[39m \n\u001b[32m    108\u001b[39m     dataloaders = {}\n",
+      "\u001b[36mFile \u001b[39m\u001b[32m~/from_ssh/DroneDetector/.venv-train/lib/python3.12/site-packages/torch/utils/data/dataloader.py:394\u001b[39m, in \u001b[36mDataLoader.__init__\u001b[39m\u001b[34m(self, dataset, batch_size, shuffle, sampler, batch_sampler, num_workers, collate_fn, pin_memory, drop_last, timeout, worker_init_fn, multiprocessing_context, generator, prefetch_factor, persistent_workers, pin_memory_device, in_order)\u001b[39m\n\u001b[32m    392\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:  \u001b[38;5;66;03m# map-style\u001b[39;00m\n\u001b[32m    393\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m shuffle:\n\u001b[32m--> \u001b[39m\u001b[32m394\u001b[39m         sampler = \u001b[30;43mRandomSampler\u001b[39;49m\u001b[30;43m(\u001b[39;49m\u001b[30;43mdataset\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mgenerator\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mgenerator\u001b[39;49m\u001b[30;43m)\u001b[39;49m  \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m    395\u001b[39m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m    396\u001b[39m         sampler = SequentialSampler(dataset)  \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n",
+      "\u001b[36mFile \u001b[39m\u001b[32m~/from_ssh/DroneDetector/.venv-train/lib/python3.12/site-packages/torch/utils/data/sampler.py:149\u001b[39m, in \u001b[36mRandomSampler.__init__\u001b[39m\u001b[34m(self, data_source, replacement, num_samples, generator)\u001b[39m\n\u001b[32m    144\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\n\u001b[32m    145\u001b[39m         \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mreplacement should be a boolean value, but got replacement=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.replacement\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m    146\u001b[39m     )\n\u001b[32m    148\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m.num_samples, \u001b[38;5;28mint\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m.num_samples <= \u001b[32m0\u001b[39m:\n\u001b[32m--> \u001b[39m\u001b[32m149\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m    150\u001b[39m         \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mnum_samples should be a positive integer value, but got num_samples=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.num_samples\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m    151\u001b[39m     )\n",
       "\u001b[31mValueError\u001b[39m: num_samples should be a positive integer value, but got num_samples=0"
      ]
     }
@@ -393,7 +389,7 @@
     "cv2.destroyAllWindows()\n",
     "gc.collect()\n",
     "\n",
-    "num_classes = 3\n",
+    "num_classes = 2\n",
     "config_name = \"ensemble\"\n",
     "    \n",
     "def load_function(attr):\n",
@@ -404,31 +400,27 @@
     "\n",
     "model1 = models.resnet18(pretrained=False)\n",
     "model2 = models.resnet50(pretrained=False)\n",
-    "model3 = models.resnet101(pretrained=False)\n",
     "\n",
     "num_classes = 2\n",
     "\n",
     "model1.fc = nn.Linear(model1.fc.in_features, num_classes)\n",
     "model2.fc = nn.Linear(model2.fc.in_features, num_classes)\n",
-    "model3.fc = nn.Linear(model3.fc.in_features, num_classes)\n",
     "\n",
     "class Ensemble(nn.Module):\n",
-    "    def __init__(self, model1, model2, model3):\n",
+    "    def __init__(self, model1, model2):\n",
     "        super(Ensemble, self).__init__()\n",
     "        self.model1 = model1\n",
     "        self.model2 = model2\n",
-    "        self.model3 = model3\n",
-    "        self.fc = nn.Linear(3 * num_classes, num_classes)\n",
+    "        self.fc = nn.Linear(2 * num_classes, num_classes)\n",
     "\n",
     "    def forward(self, x):\n",
     "        x1 = self.model1(x[0])\n",
     "        x2 = self.model2(x[1])\n",
-    "        x3 = self.model3(x[2])\n",
-    "        x = torch.cat((x1, x2, x3), dim=1)\n",
+    "        x = torch.cat((x1, x2), dim=1)\n",
     "        x = self.fc(x)\n",
     "        return x\n",
     "\n",
-    "model = Ensemble(model1, model2, model3)\n",
+    "model = Ensemble(model1, model2)\n",
     "\n",
     "optimizer = load_function(config.optimizer.name)(model.parameters(), lr=config.optimizer.lr)\n",
     "criterion = load_function(config.loss_function.name)()\n",
@@ -439,8 +431,8 @@
     "\n",
     "#----------Создания датасета и обучение модели--------------\n",
     "\n",
-    "path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 1000, path_dataset = \"/home/sibsci/dataset_img\", \n",
-    "                     selected_freq=5800,model_name = config_name+\"_5.8_jpg_\", config_name = config_name, model=model)\n",
+    "path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 10000, path_dataset = \"/mnt/data/Dataset_img\", \n",
+    "                     selected_freq=2400,model_name = config_name+\"_2.4_jpg_\", config_name = config_name, model=model)\n",
     "\n",
     "\n",
     "torch.cuda.empty_cache()\n",
@@ -461,7 +453,7 @@
  "metadata": {
   "celltoolbar": "Отсутствует",
   "kernelspec": {
-   "display_name": ".venv-train (3.12.3)",
+   "display_name": ".venv-train",
    "language": "python",
    "name": "python3"
   },

train_scripts/Training_models_2.4-Copy1.ipynb

@@ -0,0 +1,465 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "5a13ad6b-56c9-4381-b376-1765f6dd7553",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Импортирование библиотек"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7311cb4a-5bf3-4268-b431-43eea10e9ed6",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "from torch import default_generator, randperm\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "import torchvision.transforms as transforms\n",
+    "from torchvision.io import read_image\n",
+    "from importlib import import_module\n",
+    "import matplotlib.pyplot as plt\n",
+    "from torchvision import models\n",
+    "import torch, torchvision\n",
+    "from pathlib import Path\n",
+    "from PIL import Image\n",
+    "import torch.nn as nn\n",
+    "from tqdm import tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib\n",
+    "import os, shutil\n",
+    "import mlconfig\n",
+    "import random\n",
+    "import shutil\n",
+    "import timeit\n",
+    "import copy\n",
+    "import time\n",
+    "import cv2\n",
+    "import csv\n",
+    "import sys\n",
+    "import io\n",
+    "import gc\n",
+    "\n",
+    "plt.rcParams[\"savefig.bbox\"] = 'tight'\n",
+    "torch.manual_seed(1)\n",
+    "#matplotlib.use('Agg')\n",
+    "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
+    "print(device)\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "384de097-82c6-41f5-bda9-b2f54bc99593",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Подготовка и обучение детектирование"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "46e4dc99-6994-4fee-a32e-f3983bd991bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prepare_and_learning_detection(num_classes, num_samples, path_dataset, model_name, config_name, model):\n",
+    "    num_samples_per_class = num_samples // num_classes\n",
+    "\n",
+    "    #----------Создаём папку для сохранения результатов обучения--------------\n",
+    "    \n",
+    "    ind = 1\n",
+    "    while True:\n",
+    "        if os.path.exists(\"models/\" + model_name + str(ind)):\n",
+    "            ind += 1\n",
+    "        else:\n",
+    "            os.mkdir(\"models/\" + model_name + str(ind))\n",
+    "            path_res = \"models/\" + model_name + str(ind) + '/'\n",
+    "            break\n",
+    "    \n",
+    "    #----------Создаём файл dataset.csv для обучения--------------\n",
+    "    \n",
+    "    pd_columns = ['file_name']\n",
+    "    df = pd.DataFrame(columns=pd_columns)\n",
+    "    \n",
+    "    subdirs = os.listdir(path_dataset)\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        num_samples_per_class = min(num_samples_per_class, len(files))\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        random.shuffle(files)\n",
+    "        files_to_process = files[:num_samples_per_class]\n",
+    "        for file in files_to_process:\n",
+    "            row = pd.DataFrame({pd_columns[0]: [str(path_dataset + subdir + '/' + file)]})\n",
+    "            df = pd.concat([df, row], ignore_index=True)\n",
+    "    \n",
+    "    df.to_csv(path_res + 'dataset.csv', index=False)\n",
+    "    \n",
+    "    #----------Импортируем параметры для обучения--------------\n",
+    "    \n",
+    "    def load_function(attr):\n",
+    "        module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "        return getattr(import_module(module_), func)\n",
+    "    \n",
+    "    config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "    \n",
+    "    #----------Создаём класс датасета--------------\n",
+    "    \n",
+    "    class MyDataset(Dataset):\n",
+    "        def __init__(self, path_dataset, csv_file):\n",
+    "            data=[]\n",
+    "            with open(path_dataset + csv_file, newline='') as csvfile:\n",
+    "                reader = csv.reader(csvfile, delimiter=' ', quotechar='|')\n",
+    "                for row in list(reader)[1:]:\n",
+    "                    row = str(row)\n",
+    "                    data.append(row[2: len(row)-2])\n",
+    "            self.sig_filenames = data\n",
+    "            self.path_dataset = path_dataset\n",
+    "    \n",
+    "        def __len__(self):\n",
+    "            return len(self.sig_filenames)\n",
+    "    \n",
+    "        def __getitem__(self, idx):\n",
+    "            image_real = np.asarray(cv2.split(cv2.imread(self.sig_filenames[idx][:-8]+'real.jpg')), dtype=np.float32)\n",
+    "            if 'drone' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(0)\n",
+    "            if 'noise' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(1)\n",
+    "            return image_real, label\n",
+    "    \n",
+    "    #----------Создаём датасет--------------\n",
+    "    \n",
+    "    dataset = MyDataset(path_dataset=path_res, csv_file='dataset.csv')\n",
+    "    train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n",
+    "    batch_size = config.batch_size\n",
+    "    train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    valid_dataloader = torch.utils.data.DataLoader(valid_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    \n",
+    "    dataloaders = {}\n",
+    "    dataloaders['train'] = train_dataloader\n",
+    "    dataloaders['val'] = valid_dataloader\n",
+    "    dataset_sizes = {}\n",
+    "    dataset_sizes['train'] = len(train_set)\n",
+    "    dataset_sizes['val'] = len(valid_set)\n",
+    "\n",
+    "    #----------Обучаем модель--------------\n",
+    "\n",
+    "    val_loss = []\n",
+    "    val_acc = []\n",
+    "    train_loss = []\n",
+    "    train_acc = []\n",
+    "    epochs = config.epoch\n",
+    "    \n",
+    "    best_acc = 0.0\n",
+    "    best_model = copy.deepcopy(model.state_dict())\n",
+    "    limit = config.limit\n",
+    "    epoch_limit = epochs\n",
+    "    \n",
+    "    start = timeit.default_timer()\n",
+    "    for epoch in range(1, epochs+1):\n",
+    "        print(f\"Epoch : {epoch}\\n\")\n",
+    "        dataloader = None\n",
+    "    \n",
+    "        for phase in ['train', 'val']:\n",
+    "            running_loss = 0.0\n",
+    "            running_corrects = 0\n",
+    "    \n",
+    "            for (img, label) in tqdm(dataloaders[phase]):\n",
+    "                img, label = img.to(device), label.to(device)\n",
+    "                optimizer.zero_grad()\n",
+    "    \n",
+    "                with torch.set_grad_enabled(phase == 'train'):\n",
+    "                    output = model(img)\n",
+    "                    _, pred = torch.max(output.data, 1)\n",
+    "                    loss = criterion(output, label)\n",
+    "                    if phase=='train' :\n",
+    "                        loss.backward()\n",
+    "                        optimizer.step()\n",
+    "                \n",
+    "                running_loss += loss.item() * img.size(0)\n",
+    "                running_corrects += torch.sum(pred == label.data)\n",
+    "    \n",
+    "            epoch_loss = running_loss / dataset_sizes[phase]\n",
+    "            epoch_acc = running_corrects.double() / dataset_sizes[phase]\n",
+    "                \n",
+    "            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n",
+    "                    \n",
+    "            if phase=='train' :\n",
+    "                train_loss.append(epoch_loss)\n",
+    "                train_acc.append(epoch_acc)\n",
+    "            else :\n",
+    "                val_loss.append(epoch_loss)\n",
+    "                val_acc.append(epoch_acc)\n",
+    "                if val_acc[-1] > best_acc :\n",
+    "                    ind_limit = 0\n",
+    "                    best_acc = val_acc[-1]\n",
+    "                    best_model = copy.deepcopy(model.state_dict())\n",
+    "                    torch.save(best_model, path_res + model_name + '.pth')\n",
+    "                else:\n",
+    "                    ind_limit += 1\n",
+    "                    \n",
+    "                if ind_limit >= limit:\n",
+    "                    break\n",
+    "                \n",
+    "        if ind_limit >= limit:\n",
+    "            epoch_limit = epoch\n",
+    "            break\n",
+    "            \n",
+    "        print()\n",
+    "    \n",
+    "    end = timeit.default_timer()\n",
+    "    print(f\"Total time elapsed = {end - start} seconds\")\n",
+    "    epoch_limit += 1\n",
+    "    \n",
+    "    #----------Вывод графиков и сохранение результатов обучения--------------\n",
+    "    \n",
+    "    train_acc = np.asarray(list(map(lambda x: x.item(), train_acc)))\n",
+    "    val_acc = np.asarray(list(map(lambda x: x.item(), val_acc)))\n",
+    "    \n",
+    "    np.save(path_res+'train_acc.npy', train_acc)\n",
+    "    np.save(path_res+'val_acc.npy', val_acc)\n",
+    "    np.save(path_res+'train_loss.npy', train_loss)\n",
+    "    np.save(path_res+'val_loss.npy', val_loss)\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_loss, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_loss, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Loss')\n",
+    "    plt.title('Loss Curve')\n",
+    "    plt.legend(['Train Loss', 'Validation Loss'])\n",
+    "    plt.show()\n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_acc, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_acc, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Accuracy')\n",
+    "    plt.title('Accuracy Curve')\n",
+    "    plt.legend(['Train Accuracy', 'Validation Accuracy'])\n",
+    "    plt.show()\n",
+    "    \n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    torch.cuda.empty_cache()\n",
+    "    cv2.destroyAllWindows()\n",
+    "    del model\n",
+    "    gc.collect()\n",
+    "\n",
+    "    return path_res, model_name"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93c136ee",
+   "metadata": {},
+   "source": [
+    "### Ensemble"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "52e8d4c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.\n",
+      "  warnings.warn(msg)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch : 1\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|                                                                                          | 0/337 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([], device='cuda:0', size=(4, 0))\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "ename": "RuntimeError",
+     "evalue": "Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [4, 0]",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[10], line 42\u001b[0m\n\u001b[0;32m     38\u001b[0m     model \u001b[38;5;241m=\u001b[39m model\u001b[38;5;241m.\u001b[39mto(device)\n\u001b[0;32m     40\u001b[0m \u001b[38;5;66;03m#----------Создания датасета и обучение модели--------------\u001b[39;00m\n\u001b[1;32m---> 42\u001b[0m path_res, model_name \u001b[38;5;241m=\u001b[39m \u001b[43mprepare_and_learning_detection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnum_classes\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mnum_classes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_samples\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m20000\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath_dataset\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m//192.168.11.63/data/DATASETS/Energomash/2400_learning/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[0;32m     43\u001b[0m \u001b[43m                     \u001b[49m\u001b[43mmodel_name\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mconfig_name\u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m_2.4_jpg_\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig_name\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mconfig_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     46\u001b[0m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mempty_cache()\n\u001b[0;32m     47\u001b[0m cv2\u001b[38;5;241m.\u001b[39mdestroyAllWindows()\n",
+      "Cell \u001b[1;32mIn[2], line 108\u001b[0m, in \u001b[0;36mprepare_and_learning_detection\u001b[1;34m(num_classes, num_samples, path_dataset, model_name, config_name, model)\u001b[0m\n\u001b[0;32m    105\u001b[0m optimizer\u001b[38;5;241m.\u001b[39mzero_grad()\n\u001b[0;32m    107\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mset_grad_enabled(phase \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtrain\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[1;32m--> 108\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    109\u001b[0m     _, pred \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mmax(output\u001b[38;5;241m.\u001b[39mdata, \u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m    110\u001b[0m     loss \u001b[38;5;241m=\u001b[39m criterion(output, label)\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1551\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1560\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1561\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1565\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "Cell \u001b[1;32mIn[10], line 28\u001b[0m, in \u001b[0;36mModel.forward\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m     26\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, x):\n\u001b[0;32m     27\u001b[0m     \u001b[38;5;28mprint\u001b[39m(x)\n\u001b[1;32m---> 28\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     29\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m x\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1551\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1560\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1561\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1565\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\resnet.py:285\u001b[0m, in \u001b[0;36mResNet.forward\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m    284\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, x: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[1;32m--> 285\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_forward_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\resnet.py:268\u001b[0m, in \u001b[0;36mResNet._forward_impl\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m    266\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_forward_impl\u001b[39m(\u001b[38;5;28mself\u001b[39m, x: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m    267\u001b[0m     \u001b[38;5;66;03m# See note [TorchScript super()]\u001b[39;00m\n\u001b[1;32m--> 268\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconv1\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    269\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbn1(x)\n\u001b[0;32m    270\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrelu(x)\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1551\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1560\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1561\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1565\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\conv.py:458\u001b[0m, in \u001b[0;36mConv2d.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    457\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[1;32m--> 458\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_conv_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\conv.py:454\u001b[0m, in \u001b[0;36mConv2d._conv_forward\u001b[1;34m(self, input, weight, bias)\u001b[0m\n\u001b[0;32m    450\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpadding_mode \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mzeros\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[0;32m    451\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m F\u001b[38;5;241m.\u001b[39mconv2d(F\u001b[38;5;241m.\u001b[39mpad(\u001b[38;5;28minput\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reversed_padding_repeated_twice, mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpadding_mode),\n\u001b[0;32m    452\u001b[0m                     weight, bias, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstride,\n\u001b[0;32m    453\u001b[0m                     _pair(\u001b[38;5;241m0\u001b[39m), \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdilation, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgroups)\n\u001b[1;32m--> 454\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconv2d\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbias\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstride\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    455\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpadding\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdilation\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgroups\u001b[49m\u001b[43m)\u001b[49m\n",
+      "\u001b[1;31mRuntimeError\u001b[0m: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [4, 0]"
+     ]
+    }
+   ],
+   "source": [
+    "#----------Инициализируем модель и параметры обучения--------------\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()\n",
+    "\n",
+    "config_name = \"ensemble\"\n",
+    "    \n",
+    "def load_function(attr):\n",
+    "    module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "    return getattr(import_module(module_), func)\n",
+    "    \n",
+    "config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "\n",
+    "model = models.resnet18(pretrained=True)\n",
+    "\n",
+    "num_classes = 2\n",
+    "\n",
+    "model.fc = nn.Linear(model.fc.in_features, num_classes)\n",
+    "\n",
+    "class Model(nn.Module):\n",
+    "    def __init__(self, model):\n",
+    "        super(Model, self).__init__()\n",
+    "        self.model = model\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        print(x)\n",
+    "        x = self.model(x)\n",
+    "        return x\n",
+    "\n",
+    "model = Model(model)\n",
+    "\n",
+    "optimizer = load_function(config.optimizer.name)(model.parameters(), lr=config.optimizer.lr)\n",
+    "criterion = load_function(config.loss_function.name)()\n",
+    "scheduler = load_function(config.scheduler.name)(optimizer, step_size=config.scheduler.step_size, gamma=config.scheduler.gamma)\n",
+    "\n",
+    "if device != 'cpu':\n",
+    "    model = model.to(device)\n",
+    "\n",
+    "#----------Создания датасета и обучение модели--------------\n",
+    "\n",
+    "path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 20000, path_dataset = \"//192.168.11.63/data/DATASETS/Energomash/2400_learning/\", \n",
+    "                     model_name = config_name+\"_2.4_jpg_\", config_name = config_name, model=model)\n",
+    "\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "del model\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "57d18676",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c10afb29",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "celltoolbar": "Отсутствует",
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/Training_models_2.4-Copy3.ipynb

@@ -0,0 +1,465 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "5a13ad6b-56c9-4381-b376-1765f6dd7553",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Импортирование библиотек"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7311cb4a-5bf3-4268-b431-43eea10e9ed6",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "from torch import default_generator, randperm\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "import torchvision.transforms as transforms\n",
+    "from torchvision.io import read_image\n",
+    "from importlib import import_module\n",
+    "import matplotlib.pyplot as plt\n",
+    "from torchvision import models\n",
+    "import torch, torchvision\n",
+    "from pathlib import Path\n",
+    "from PIL import Image\n",
+    "import torch.nn as nn\n",
+    "from tqdm import tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib\n",
+    "import os, shutil\n",
+    "import mlconfig\n",
+    "import random\n",
+    "import shutil\n",
+    "import timeit\n",
+    "import copy\n",
+    "import time\n",
+    "import cv2\n",
+    "import csv\n",
+    "import sys\n",
+    "import io\n",
+    "import gc\n",
+    "\n",
+    "plt.rcParams[\"savefig.bbox\"] = 'tight'\n",
+    "torch.manual_seed(1)\n",
+    "#matplotlib.use('Agg')\n",
+    "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
+    "print(device)\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "384de097-82c6-41f5-bda9-b2f54bc99593",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Подготовка и обучение детектирование"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "46e4dc99-6994-4fee-a32e-f3983bd991bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prepare_and_learning_detection(num_classes, num_samples, path_dataset, model_name, config_name, model):\n",
+    "    num_samples_per_class = num_samples // num_classes\n",
+    "\n",
+    "    #----------Создаём папку для сохранения результатов обучения--------------\n",
+    "    \n",
+    "    ind = 1\n",
+    "    while True:\n",
+    "        if os.path.exists(\"models/\" + model_name + str(ind)):\n",
+    "            ind += 1\n",
+    "        else:\n",
+    "            os.mkdir(\"models/\" + model_name + str(ind))\n",
+    "            path_res = \"models/\" + model_name + str(ind) + '/'\n",
+    "            break\n",
+    "    \n",
+    "    #----------Создаём файл dataset.csv для обучения--------------\n",
+    "    \n",
+    "    pd_columns = ['file_name']\n",
+    "    df = pd.DataFrame(columns=pd_columns)\n",
+    "    \n",
+    "    subdirs = os.listdir(path_dataset)\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        num_samples_per_class = min(num_samples_per_class, len(files))\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        random.shuffle(files)\n",
+    "        files_to_process = files[:num_samples_per_class]\n",
+    "        for file in files_to_process:\n",
+    "            row = pd.DataFrame({pd_columns[0]: [str(path_dataset + subdir + '/' + file)]})\n",
+    "            df = pd.concat([df, row], ignore_index=True)\n",
+    "    \n",
+    "    df.to_csv(path_res + 'dataset.csv', index=False)\n",
+    "    \n",
+    "    #----------Импортируем параметры для обучения--------------\n",
+    "    \n",
+    "    def load_function(attr):\n",
+    "        module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "        return getattr(import_module(module_), func)\n",
+    "    \n",
+    "    config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "    \n",
+    "    #----------Создаём класс датасета--------------\n",
+    "    \n",
+    "    class MyDataset(Dataset):\n",
+    "        def __init__(self, path_dataset, csv_file):\n",
+    "            data=[]\n",
+    "            with open(path_dataset + csv_file, newline='') as csvfile:\n",
+    "                reader = csv.reader(csvfile, delimiter=' ', quotechar='|')\n",
+    "                for row in list(reader)[1:]:\n",
+    "                    row = str(row)\n",
+    "                    data.append(row[2: len(row)-2])\n",
+    "            self.sig_filenames = data\n",
+    "            self.path_dataset = path_dataset\n",
+    "    \n",
+    "        def __len__(self):\n",
+    "            return len(self.sig_filenames)\n",
+    "    \n",
+    "        def __getitem__(self, idx):\n",
+    "            image_real = np.asarray(cv2.split(cv2.imread(self.sig_filenames[idx][:-8]+'real.jpg')), dtype=np.float32)\n",
+    "            if 'drone' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(0)\n",
+    "            if 'noise' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(1)\n",
+    "            return image_real, label\n",
+    "    \n",
+    "    #----------Создаём датасет--------------\n",
+    "    \n",
+    "    dataset = MyDataset(path_dataset=path_res, csv_file='dataset.csv')\n",
+    "    train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n",
+    "    batch_size = config.batch_size\n",
+    "    train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    valid_dataloader = torch.utils.data.DataLoader(valid_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    \n",
+    "    dataloaders = {}\n",
+    "    dataloaders['train'] = train_dataloader\n",
+    "    dataloaders['val'] = valid_dataloader\n",
+    "    dataset_sizes = {}\n",
+    "    dataset_sizes['train'] = len(train_set)\n",
+    "    dataset_sizes['val'] = len(valid_set)\n",
+    "\n",
+    "    #----------Обучаем модель--------------\n",
+    "\n",
+    "    val_loss = []\n",
+    "    val_acc = []\n",
+    "    train_loss = []\n",
+    "    train_acc = []\n",
+    "    epochs = config.epoch\n",
+    "    \n",
+    "    best_acc = 0.0\n",
+    "    best_model = copy.deepcopy(model.state_dict())\n",
+    "    limit = config.limit\n",
+    "    epoch_limit = epochs\n",
+    "    \n",
+    "    start = timeit.default_timer()\n",
+    "    for epoch in range(1, epochs+1):\n",
+    "        print(f\"Epoch : {epoch}\\n\")\n",
+    "        dataloader = None\n",
+    "    \n",
+    "        for phase in ['train', 'val']:\n",
+    "            running_loss = 0.0\n",
+    "            running_corrects = 0\n",
+    "    \n",
+    "            for (img, label) in tqdm(dataloaders[phase]):\n",
+    "                img, label = img.to(device), label.to(device)\n",
+    "                optimizer.zero_grad()\n",
+    "    \n",
+    "                with torch.set_grad_enabled(phase == 'train'):\n",
+    "                    output = model(img)\n",
+    "                    _, pred = torch.max(output.data, 1)\n",
+    "                    loss = criterion(output, label)\n",
+    "                    if phase=='train' :\n",
+    "                        loss.backward()\n",
+    "                        optimizer.step()\n",
+    "                \n",
+    "                running_loss += loss.item() * img.size(0)\n",
+    "                running_corrects += torch.sum(pred == label.data)\n",
+    "    \n",
+    "            epoch_loss = running_loss / dataset_sizes[phase]\n",
+    "            epoch_acc = running_corrects.double() / dataset_sizes[phase]\n",
+    "                \n",
+    "            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n",
+    "                    \n",
+    "            if phase=='train' :\n",
+    "                train_loss.append(epoch_loss)\n",
+    "                train_acc.append(epoch_acc)\n",
+    "            else :\n",
+    "                val_loss.append(epoch_loss)\n",
+    "                val_acc.append(epoch_acc)\n",
+    "                if val_acc[-1] > best_acc :\n",
+    "                    ind_limit = 0\n",
+    "                    best_acc = val_acc[-1]\n",
+    "                    best_model = copy.deepcopy(model.state_dict())\n",
+    "                    torch.save(best_model, path_res + model_name + '.pth')\n",
+    "                else:\n",
+    "                    ind_limit += 1\n",
+    "                    \n",
+    "                if ind_limit >= limit:\n",
+    "                    break\n",
+    "                \n",
+    "        if ind_limit >= limit:\n",
+    "            epoch_limit = epoch\n",
+    "            break\n",
+    "            \n",
+    "        print()\n",
+    "    \n",
+    "    end = timeit.default_timer()\n",
+    "    print(f\"Total time elapsed = {end - start} seconds\")\n",
+    "    epoch_limit += 1\n",
+    "    \n",
+    "    #----------Вывод графиков и сохранение результатов обучения--------------\n",
+    "    \n",
+    "    train_acc = np.asarray(list(map(lambda x: x.item(), train_acc)))\n",
+    "    val_acc = np.asarray(list(map(lambda x: x.item(), val_acc)))\n",
+    "    \n",
+    "    np.save(path_res+'train_acc.npy', train_acc)\n",
+    "    np.save(path_res+'val_acc.npy', val_acc)\n",
+    "    np.save(path_res+'train_loss.npy', train_loss)\n",
+    "    np.save(path_res+'val_loss.npy', val_loss)\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_loss, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_loss, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Loss')\n",
+    "    plt.title('Loss Curve')\n",
+    "    plt.legend(['Train Loss', 'Validation Loss'])\n",
+    "    plt.show()\n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_acc, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_acc, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Accuracy')\n",
+    "    plt.title('Accuracy Curve')\n",
+    "    plt.legend(['Train Accuracy', 'Validation Accuracy'])\n",
+    "    plt.show()\n",
+    "    \n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    torch.cuda.empty_cache()\n",
+    "    cv2.destroyAllWindows()\n",
+    "    del model\n",
+    "    gc.collect()\n",
+    "\n",
+    "    return path_res, model_name"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93c136ee",
+   "metadata": {},
+   "source": [
+    "### Ensemble"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "52e8d4c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.\n",
+      "  warnings.warn(msg)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch : 1\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|                                                                                          | 0/337 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([], device='cuda:0', size=(4, 0))\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "ename": "RuntimeError",
+     "evalue": "Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [4, 0]",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[10], line 42\u001b[0m\n\u001b[0;32m     38\u001b[0m     model \u001b[38;5;241m=\u001b[39m model\u001b[38;5;241m.\u001b[39mto(device)\n\u001b[0;32m     40\u001b[0m \u001b[38;5;66;03m#----------Создания датасета и обучение модели--------------\u001b[39;00m\n\u001b[1;32m---> 42\u001b[0m path_res, model_name \u001b[38;5;241m=\u001b[39m \u001b[43mprepare_and_learning_detection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnum_classes\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mnum_classes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_samples\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m20000\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath_dataset\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m//192.168.11.63/data/DATASETS/Energomash/2400_learning/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[0;32m     43\u001b[0m \u001b[43m                     \u001b[49m\u001b[43mmodel_name\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mconfig_name\u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m_2.4_jpg_\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig_name\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mconfig_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     46\u001b[0m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mempty_cache()\n\u001b[0;32m     47\u001b[0m cv2\u001b[38;5;241m.\u001b[39mdestroyAllWindows()\n",
+      "Cell \u001b[1;32mIn[2], line 108\u001b[0m, in \u001b[0;36mprepare_and_learning_detection\u001b[1;34m(num_classes, num_samples, path_dataset, model_name, config_name, model)\u001b[0m\n\u001b[0;32m    105\u001b[0m optimizer\u001b[38;5;241m.\u001b[39mzero_grad()\n\u001b[0;32m    107\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mset_grad_enabled(phase \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtrain\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[1;32m--> 108\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    109\u001b[0m     _, pred \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mmax(output\u001b[38;5;241m.\u001b[39mdata, \u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m    110\u001b[0m     loss \u001b[38;5;241m=\u001b[39m criterion(output, label)\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1551\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1560\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1561\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1565\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "Cell \u001b[1;32mIn[10], line 28\u001b[0m, in \u001b[0;36mModel.forward\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m     26\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, x):\n\u001b[0;32m     27\u001b[0m     \u001b[38;5;28mprint\u001b[39m(x)\n\u001b[1;32m---> 28\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     29\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m x\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1551\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1560\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1561\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1565\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\resnet.py:285\u001b[0m, in \u001b[0;36mResNet.forward\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m    284\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, x: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[1;32m--> 285\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_forward_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\resnet.py:268\u001b[0m, in \u001b[0;36mResNet._forward_impl\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m    266\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_forward_impl\u001b[39m(\u001b[38;5;28mself\u001b[39m, x: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m    267\u001b[0m     \u001b[38;5;66;03m# See note [TorchScript super()]\u001b[39;00m\n\u001b[1;32m--> 268\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconv1\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    269\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbn1(x)\n\u001b[0;32m    270\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrelu(x)\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1551\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1560\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1561\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1565\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\conv.py:458\u001b[0m, in \u001b[0;36mConv2d.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    457\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[1;32m--> 458\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_conv_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\miniconda3\\envs\\python311\\Lib\\site-packages\\torch\\nn\\modules\\conv.py:454\u001b[0m, in \u001b[0;36mConv2d._conv_forward\u001b[1;34m(self, input, weight, bias)\u001b[0m\n\u001b[0;32m    450\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpadding_mode \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mzeros\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[0;32m    451\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m F\u001b[38;5;241m.\u001b[39mconv2d(F\u001b[38;5;241m.\u001b[39mpad(\u001b[38;5;28minput\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reversed_padding_repeated_twice, mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpadding_mode),\n\u001b[0;32m    452\u001b[0m                     weight, bias, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstride,\n\u001b[0;32m    453\u001b[0m                     _pair(\u001b[38;5;241m0\u001b[39m), \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdilation, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgroups)\n\u001b[1;32m--> 454\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconv2d\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbias\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstride\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    455\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpadding\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdilation\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgroups\u001b[49m\u001b[43m)\u001b[49m\n",
+      "\u001b[1;31mRuntimeError\u001b[0m: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [4, 0]"
+     ]
+    }
+   ],
+   "source": [
+    "#----------Инициализируем модель и параметры обучения--------------\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()\n",
+    "\n",
+    "config_name = \"ensemble\"\n",
+    "    \n",
+    "def load_function(attr):\n",
+    "    module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "    return getattr(import_module(module_), func)\n",
+    "    \n",
+    "config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "\n",
+    "model = models.resnet18(pretrained=True)\n",
+    "\n",
+    "num_classes = 2\n",
+    "\n",
+    "model.fc = nn.Linear(model.fc.in_features, num_classes)\n",
+    "\n",
+    "class Model(nn.Module):\n",
+    "    def __init__(self, model):\n",
+    "        super(Model, self).__init__()\n",
+    "        self.model = model\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        print(x)\n",
+    "        x = self.model(x)\n",
+    "        return x\n",
+    "\n",
+    "model = Model(model)\n",
+    "\n",
+    "optimizer = load_function(config.optimizer.name)(model.parameters(), lr=config.optimizer.lr)\n",
+    "criterion = load_function(config.loss_function.name)()\n",
+    "scheduler = load_function(config.scheduler.name)(optimizer, step_size=config.scheduler.step_size, gamma=config.scheduler.gamma)\n",
+    "\n",
+    "if device != 'cpu':\n",
+    "    model = model.to(device)\n",
+    "\n",
+    "#----------Создания датасета и обучение модели--------------\n",
+    "\n",
+    "path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 20000, path_dataset = \"//192.168.11.63/data/DATASETS/Energomash/2400_learning/\", \n",
+    "                     model_name = config_name+\"_2.4_jpg_\", config_name = config_name, model=model)\n",
+    "\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "del model\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "57d18676",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c10afb29",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "celltoolbar": "Отсутствует",
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/Training_models_915.ipynb

@@ -0,0 +1,503 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "5a13ad6b-56c9-4381-b376-1765f6dd7553",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Импортирование библиотек"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7311cb4a-5bf3-4268-b431-43eea10e9ed6",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cuda\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "12"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "from torch import default_generator, randperm\n",
+    "from torch.utils.data.dataset import Subset\n",
+    "import torchvision.transforms as transforms\n",
+    "from torchvision.io import read_image\n",
+    "from importlib import import_module\n",
+    "import matplotlib.pyplot as plt\n",
+    "from torchvision import models\n",
+    "import torch, torchvision\n",
+    "from pathlib import Path\n",
+    "from PIL import Image\n",
+    "import torch.nn as nn\n",
+    "from tqdm import tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib\n",
+    "import os, shutil\n",
+    "import mlconfig\n",
+    "import random\n",
+    "import shutil\n",
+    "import timeit\n",
+    "import copy\n",
+    "import time\n",
+    "import cv2\n",
+    "import csv\n",
+    "import sys\n",
+    "import io\n",
+    "import gc\n",
+    "\n",
+    "plt.rcParams[\"savefig.bbox\"] = 'tight'\n",
+    "torch.manual_seed(1)\n",
+    "#matplotlib.use('Agg')\n",
+    "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
+    "print(device)\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "384de097-82c6-41f5-bda9-b2f54bc99593",
+   "metadata": {
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "# Подготовка и обучение детектирование"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "46e4dc99-6994-4fee-a32e-f3983bd991bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prepare_and_learning_detection(num_classes, num_samples, path_dataset, model_name, config_name, model):\n",
+    "    num_samples_per_class = num_samples // num_classes\n",
+    "\n",
+    "    #----------Создаём папку для сохранения результатов обучения--------------\n",
+    "    \n",
+    "    ind = 1\n",
+    "    while True:\n",
+    "        if os.path.exists(\"models/\" + model_name + str(ind)):\n",
+    "            ind += 1\n",
+    "        else:\n",
+    "            os.mkdir(\"models/\" + model_name + str(ind))\n",
+    "            path_res = \"models/\" + model_name + str(ind) + '/'\n",
+    "            break\n",
+    "    \n",
+    "    #----------Создаём файл dataset.csv для обучения--------------\n",
+    "    \n",
+    "    pd_columns = ['file_name']\n",
+    "    df = pd.DataFrame(columns=pd_columns)\n",
+    "    \n",
+    "    subdirs = os.listdir(path_dataset)\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        num_samples_per_class = min(num_samples_per_class, len(files))\n",
+    "    for subdir in subdirs:\n",
+    "        files = os.listdir(path_dataset + subdir + '/')\n",
+    "        random.shuffle(files)\n",
+    "        files_to_process = files[:num_samples_per_class]\n",
+    "        for file in files_to_process:\n",
+    "            row = pd.DataFrame({pd_columns[0]: [str(path_dataset + subdir + '/' + file)]})\n",
+    "            df = pd.concat([df, row], ignore_index=True)\n",
+    "    \n",
+    "    df.to_csv(path_res + 'dataset.csv', index=False)\n",
+    "    \n",
+    "    #----------Импортируем параметры для обучения--------------\n",
+    "    \n",
+    "    def load_function(attr):\n",
+    "        module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "        return getattr(import_module(module_), func)\n",
+    "    \n",
+    "    config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "    \n",
+    "    #----------Создаём класс датасета--------------\n",
+    "    \n",
+    "    class MyDataset(Dataset):\n",
+    "        def __init__(self, path_dataset, csv_file):\n",
+    "            data=[]\n",
+    "            with open(path_dataset + csv_file, newline='') as csvfile:\n",
+    "                reader = csv.reader(csvfile, delimiter=' ', quotechar='|')\n",
+    "                for row in list(reader)[1:]:\n",
+    "                    row = str(row)\n",
+    "                    data.append(row[2: len(row)-2])\n",
+    "            self.sig_filenames = data\n",
+    "            self.path_dataset = path_dataset\n",
+    "    \n",
+    "        def __len__(self):\n",
+    "            return len(self.sig_filenames)\n",
+    "    \n",
+    "        def __getitem__(self, idx):\n",
+    "            image_real = np.asarray(cv2.split(cv2.imread(self.sig_filenames[idx][:-8]+'real.jpg')), dtype=np.float32)\n",
+    "            image_imag = np.asarray(cv2.split(cv2.imread(self.sig_filenames[idx][:-8]+'imag.jpg')), dtype=np.float32)\n",
+    "            image_spec = np.asarray(cv2.split(cv2.imread(self.sig_filenames[idx][:-8]+'spec.jpg')), dtype=np.float32)\n",
+    "            if 'drone' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(0)\n",
+    "            if 'noise' in list(self.sig_filenames[idx].split('/')):\n",
+    "                label = torch.tensor(1)\n",
+    "            return image_real, image_imag, image_spec, label\n",
+    "    \n",
+    "    #----------Создаём датасет--------------\n",
+    "    \n",
+    "    dataset = MyDataset(path_dataset=path_res, csv_file='dataset.csv')\n",
+    "    train_set, valid_set = torch.utils.data.random_split(dataset, [0.7, 0.3], generator=torch.Generator().manual_seed(42))\n",
+    "    batch_size = config.batch_size\n",
+    "    train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    valid_dataloader = torch.utils.data.DataLoader(valid_set, batch_size=batch_size, shuffle=True, drop_last=True)\n",
+    "    \n",
+    "    dataloaders = {}\n",
+    "    dataloaders['train'] = train_dataloader\n",
+    "    dataloaders['val'] = valid_dataloader\n",
+    "    dataset_sizes = {}\n",
+    "    dataset_sizes['train'] = len(train_set)\n",
+    "    dataset_sizes['val'] = len(valid_set)\n",
+    "\n",
+    "    #----------Обучаем модель--------------\n",
+    "\n",
+    "    val_loss = []\n",
+    "    val_acc = []\n",
+    "    train_loss = []\n",
+    "    train_acc = []\n",
+    "    epochs = config.epoch\n",
+    "    \n",
+    "    best_acc = 0.0\n",
+    "    best_model = copy.deepcopy(model.state_dict())\n",
+    "    limit = config.limit\n",
+    "    epoch_limit = epochs\n",
+    "    \n",
+    "    start = timeit.default_timer()\n",
+    "    for epoch in range(1, epochs+1):\n",
+    "        print(f\"Epoch : {epoch}\\n\")\n",
+    "        dataloader = None\n",
+    "    \n",
+    "        for phase in ['train', 'val']:\n",
+    "            running_loss = 0.0\n",
+    "            running_corrects = 0\n",
+    "    \n",
+    "            for (img1, img2, img3, label) in tqdm(dataloaders[phase]):\n",
+    "                img1, img2, img3, label = img1.to(device), img2.to(device), img3.to(device), label.to(device)\n",
+    "                optimizer.zero_grad()\n",
+    "    \n",
+    "                with torch.set_grad_enabled(phase == 'train'):\n",
+    "                    output = model([img1, img2, img3])\n",
+    "                    _, pred = torch.max(output.data, 1)\n",
+    "                    loss = criterion(output, label)\n",
+    "                    if phase=='train' :\n",
+    "                        loss.backward()\n",
+    "                        optimizer.step()\n",
+    "                \n",
+    "                running_loss += loss.item() * 3 * img1.size(0)\n",
+    "                running_corrects += torch.sum(pred == label.data)\n",
+    "    \n",
+    "            epoch_loss = running_loss / dataset_sizes[phase]\n",
+    "            epoch_acc = running_corrects.double() / dataset_sizes[phase]\n",
+    "                \n",
+    "            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n",
+    "                    \n",
+    "            if phase=='train' :\n",
+    "                train_loss.append(epoch_loss)\n",
+    "                train_acc.append(epoch_acc)\n",
+    "            else :\n",
+    "                val_loss.append(epoch_loss)\n",
+    "                val_acc.append(epoch_acc)\n",
+    "                if val_acc[-1] > best_acc :\n",
+    "                    ind_limit = 0\n",
+    "                    best_acc = val_acc[-1]\n",
+    "                    best_model = copy.deepcopy(model.state_dict())\n",
+    "                    torch.save(best_model, path_res + model_name + '.pth')\n",
+    "                else:\n",
+    "                    ind_limit += 1\n",
+    "                    \n",
+    "                if ind_limit >= limit:\n",
+    "                    break\n",
+    "                \n",
+    "        if ind_limit >= limit:\n",
+    "            epoch_limit = epoch\n",
+    "            break\n",
+    "            \n",
+    "        print()\n",
+    "    \n",
+    "    end = timeit.default_timer()\n",
+    "    print(f\"Total time elapsed = {end - start} seconds\")\n",
+    "    epoch_limit += 1\n",
+    "    \n",
+    "    #----------Вывод графиков и сохранение результатов обучения--------------\n",
+    "    \n",
+    "    train_acc = np.asarray(list(map(lambda x: x.item(), train_acc)))\n",
+    "    val_acc = np.asarray(list(map(lambda x: x.item(), val_acc)))\n",
+    "    \n",
+    "    np.save(path_res+'train_acc.npy', train_acc)\n",
+    "    np.save(path_res+'val_acc.npy', val_acc)\n",
+    "    np.save(path_res+'train_loss.npy', train_loss)\n",
+    "    np.save(path_res+'val_loss.npy', val_loss)\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_loss, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_loss, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Loss')\n",
+    "    plt.title('Loss Curve')\n",
+    "    plt.legend(['Train Loss', 'Validation Loss'])\n",
+    "    plt.show()\n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    \n",
+    "    plt.figure()\n",
+    "    plt.plot(range(1,epoch_limit), train_acc, color='blue')\n",
+    "    plt.plot(range(1,epoch_limit), val_acc, color='red')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Accuracy')\n",
+    "    plt.title('Accuracy Curve')\n",
+    "    plt.legend(['Train Accuracy', 'Validation Accuracy'])\n",
+    "    plt.show()\n",
+    "    \n",
+    "    plt.clf()\n",
+    "    plt.cla()\n",
+    "    plt.close()\n",
+    "    torch.cuda.empty_cache()\n",
+    "    cv2.destroyAllWindows()\n",
+    "    del model\n",
+    "    gc.collect()\n",
+    "\n",
+    "    return path_res, model_name"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93c136ee",
+   "metadata": {},
+   "source": [
+    "### Ensemble"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "52e8d4c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\snytk\\miniconda3\\envs\\python311\\Lib\\site-packages\\torchvision\\models\\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.\n",
+      "  warnings.warn(msg)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch : 1\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████████████████████████████████████████████████████████████████████████| 658/658 [1:00:26<00:00,  5.51s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "train Loss: 0.6663 Acc: 0.9241\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 282/282 [02:45<00:00,  1.71it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "val Loss: 0.4023 Acc: 0.9557\n",
+      "\n",
+      "Epoch : 2\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 658/658 [43:11<00:00,  3.94s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "train Loss: 0.4096 Acc: 0.9514\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 282/282 [00:47<00:00,  5.98it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "val Loss: 0.3390 Acc: 0.9574\n",
+      "\n",
+      "Epoch : 3\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  8%|██████▍                                                                          | 52/658 [04:26<51:43,  5.12s/it]"
+     ]
+    }
+   ],
+   "source": [
+    "#----------Инициализируем модель и параметры обучения--------------\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "gc.collect()\n",
+    "\n",
+    "num_classes = 3\n",
+    "config_name = \"ensemble\"\n",
+    "    \n",
+    "def load_function(attr):\n",
+    "    module_, func = attr.rsplit('.', maxsplit=1)\n",
+    "    return getattr(import_module(module_), func)\n",
+    "    \n",
+    "config = mlconfig.load('config_' + config_name + '.yaml')\n",
+    "\n",
+    "model1 = models.resnet18(pretrained=False)\n",
+    "model2 = models.resnet50(pretrained=False)\n",
+    "model3 = models.resnet101(pretrained=False)\n",
+    "\n",
+    "num_classes = 2\n",
+    "\n",
+    "model1.fc = nn.Linear(model1.fc.in_features, num_classes)\n",
+    "model2.fc = nn.Linear(model2.fc.in_features, num_classes)\n",
+    "model3.fc = nn.Linear(model3.fc.in_features, num_classes)\n",
+    "\n",
+    "class Ensemble(nn.Module):\n",
+    "    def __init__(self, model1, model2, model3):\n",
+    "        super(Ensemble, self).__init__()\n",
+    "        self.model1 = model1\n",
+    "        self.model2 = model2\n",
+    "        self.model3 = model3\n",
+    "        self.fc = nn.Linear(3 * num_classes, num_classes)\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x1 = self.model1(x[0])\n",
+    "        x2 = self.model2(x[1])\n",
+    "        x3 = self.model3(x[2])\n",
+    "        x = torch.cat((x1, x2, x3), dim=1)\n",
+    "        x = self.fc(x)\n",
+    "        return x\n",
+    "\n",
+    "model = Ensemble(model1, model2, model3)\n",
+    "\n",
+    "optimizer = load_function(config.optimizer.name)(model.parameters(), lr=config.optimizer.lr)\n",
+    "criterion = load_function(config.loss_function.name)()\n",
+    "scheduler = load_function(config.scheduler.name)(optimizer, step_size=config.scheduler.step_size, gamma=config.scheduler.gamma)\n",
+    "\n",
+    "if device != 'cpu':\n",
+    "    model = model.to(device)\n",
+    "\n",
+    "#----------Создания датасета и обучение модели--------------\n",
+    "\n",
+    "path_res, model_name = prepare_and_learning_detection(num_classes = num_classes, num_samples = 5000, path_dataset = \"C:/Users/snytk/Lerning_NN_for_work/datasets_jpg/915_jpg_learning/\", \n",
+    "                     model_name = config_name+\"_915_jpg_\", config_name = config_name, model=model)\n",
+    "\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "cv2.destroyAllWindows()\n",
+    "del model\n",
+    "gc.collect()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "57d18676",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eab69324",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "celltoolbar": "Отсутствует",
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/Untitled.ipynb

@@ -0,0 +1,370 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "c1b1a484",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['id', 'module_id', 'createdAt', 'registeredAt', 'data', 'createdBy', 'type']\n",
+      "['291725', '1', '2025-02-14 13:58:03', '2025-02-14 13:58:01', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291722', '1', '2025-02-14 13:57:32', '2025-02-14 13:57:30', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291721', '1', '2025-02-14 13:57:29', '2025-02-14 13:57:27', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291718', '1', '2025-02-14 13:56:58', '2025-02-14 13:56:55', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291715', '1', '2025-02-14 13:56:26', '2025-02-14 13:56:24', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291711', '1', '2025-02-14 13:55:53', '2025-02-14 13:55:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291710', '1', '2025-02-14 13:55:50', '2025-02-14 13:55:48', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291706', '1', '2025-02-14 13:55:17', '2025-02-14 13:55:15', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291700', '1', '2025-02-14 13:54:15', '2025-02-14 13:54:13', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291697', '1', '2025-02-14 13:53:44', '2025-02-14 13:53:42', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291696', '1', '2025-02-14 13:53:41', '2025-02-14 13:53:39', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291693', '1', '2025-02-14 13:53:10', '2025-02-14 13:53:07', '[{\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291692', '1', '2025-02-14 13:53:07', '2025-02-14 13:53:05', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291688', '1', '2025-02-14 13:52:34', '2025-02-14 13:52:32', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291685', '1', '2025-02-14 13:52:03', '2025-02-14 13:52:01', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291684', '1', '2025-02-14 13:52:01', '2025-02-14 13:51:59', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291681', '1', '2025-02-14 13:51:30', '2025-02-14 13:51:28', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291677', '1', '2025-02-14 13:50:57', '2025-02-14 13:50:55', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291676', '1', '2025-02-14 13:50:53', '2025-02-14 13:50:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291673', '1', '2025-02-14 13:50:21', '2025-02-14 13:50:19', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291672', '1', '2025-02-14 13:50:18', '2025-02-14 13:50:16', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291669', '1', '2025-02-14 13:49:47', '2025-02-14 13:49:45', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291668', '1', '2025-02-14 13:49:36', '2025-02-14 13:49:34', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291665', '1', '2025-02-14 13:49:05', '2025-02-14 13:49:03', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291664', '1', '2025-02-14 13:49:03', '2025-02-14 13:49:01', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291661', '1', '2025-02-14 13:48:32', '2025-02-14 13:48:30', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291657', '1', '2025-02-14 13:47:59', '2025-02-14 13:47:57', '[{\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291656', '1', '2025-02-14 13:47:56', '2025-02-14 13:47:54', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291653', '1', '2025-02-14 13:47:24', '2025-02-14 13:47:22', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291621', '1', '2025-02-14 13:15:52', '2025-02-14 13:15:50', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291615', '1', '2025-02-14 13:14:50', '2025-02-14 13:14:48', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291614', '1', '2025-02-14 13:14:45', '2025-02-14 13:14:43', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291611', '1', '2025-02-14 13:14:14', '2025-02-14 13:14:12', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291607', '1', '2025-02-14 13:13:38', '2025-02-14 13:13:36', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291551', '1', '2025-02-14 12:17:59', '2025-02-14 12:17:57', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291548', '1', '2025-02-14 12:17:28', '2025-02-14 12:17:26', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291547', '1', '2025-02-14 12:17:26', '2025-02-14 12:17:24', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291544', '1', '2025-02-14 12:16:55', '2025-02-14 12:16:53', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291543', '1', '2025-02-14 12:16:51', '2025-02-14 12:16:49', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291540', '1', '2025-02-14 12:16:20', '2025-02-14 12:16:18', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291335', '1', '2025-02-14 08:51:24', '2025-02-14 08:51:22', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291332', '1', '2025-02-14 08:50:53', '2025-02-14 08:50:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291331', '1', '2025-02-14 08:50:48', '2025-02-14 08:50:46', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291328', '1', '2025-02-14 08:50:17', '2025-02-14 08:50:14', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291327', '1', '2025-02-14 08:50:11', '2025-02-14 08:50:09', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291324', '1', '2025-02-14 08:49:40', '2025-02-14 08:49:38', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291323', '1', '2025-02-14 08:49:36', '2025-02-14 08:49:34', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291320', '1', '2025-02-14 08:49:05', '2025-02-14 08:49:03', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291317', '1', '2025-02-14 08:48:34', '2025-02-14 08:48:32', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291316', '1', '2025-02-14 08:48:32', '2025-02-14 08:48:30', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291313', '1', '2025-02-14 08:48:01', '2025-02-14 08:47:59', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291312', '1', '2025-02-14 08:47:46', '2025-02-14 08:47:44', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291309', '1', '2025-02-14 08:47:15', '2025-02-14 08:47:13', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291308', '1', '2025-02-14 08:47:13', '2025-02-14 08:47:11', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291305', '1', '2025-02-14 08:46:41', '2025-02-14 08:46:39', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291304', '1', '2025-02-14 08:46:25', '2025-02-14 08:46:23', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291301', '1', '2025-02-14 08:45:54', '2025-02-14 08:45:52', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291300', '1', '2025-02-14 08:45:52', '2025-02-14 08:45:50', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291297', '1', '2025-02-14 08:45:21', '2025-02-14 08:45:19', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291296', '1', '2025-02-14 08:45:17', '2025-02-14 08:45:15', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291293', '1', '2025-02-14 08:44:46', '2025-02-14 08:44:44', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291292', '1', '2025-02-14 08:44:33', '2025-02-14 08:44:31', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291289', '1', '2025-02-14 08:44:02', '2025-02-14 08:44:00', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291288', '1', '2025-02-14 08:43:53', '2025-02-14 08:43:50', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291285', '1', '2025-02-14 08:43:21', '2025-02-14 08:43:19', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291284', '1', '2025-02-14 08:43:19', '2025-02-14 08:43:17', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291281', '1', '2025-02-14 08:42:48', '2025-02-14 08:42:46', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291280', '1', '2025-02-14 08:42:32', '2025-02-14 08:42:30', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291277', '1', '2025-02-14 08:42:01', '2025-02-14 08:41:59', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291276', '1', '2025-02-14 08:41:57', '2025-02-14 08:41:55', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291269', '1', '2025-02-14 08:40:52', '2025-02-14 08:40:50', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['291265', '1', '2025-02-14 08:40:19', '2025-02-14 08:40:17', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290775', '1', '2025-02-14 00:29:43', '2025-02-14 00:29:41', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290772', '1', '2025-02-14 00:29:12', '2025-02-14 00:29:10', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290768', '1', '2025-02-14 00:28:38', '2025-02-14 00:28:36', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290767', '1', '2025-02-14 00:28:27', '2025-02-14 00:28:25', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290764', '1', '2025-02-14 00:27:56', '2025-02-14 00:27:54', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290763', '1', '2025-02-14 00:27:46', '2025-02-14 00:27:44', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290760', '1', '2025-02-14 00:27:15', '2025-02-14 00:27:13', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290756', '1', '2025-02-14 00:26:42', '2025-02-14 00:26:40', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290752', '1', '2025-02-14 00:25:59', '2025-02-14 00:25:57', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290748', '1', '2025-02-14 00:25:26', '2025-02-14 00:25:24', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290744', '1', '2025-02-14 00:24:51', '2025-02-14 00:24:49', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290743', '1', '2025-02-14 00:24:41', '2025-02-14 00:24:39', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290740', '1', '2025-02-14 00:24:10', '2025-02-14 00:24:08', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290739', '1', '2025-02-14 00:24:00', '2025-02-14 00:23:58', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290736', '1', '2025-02-14 00:23:29', '2025-02-14 00:23:27', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290735', '1', '2025-02-14 00:23:24', '2025-02-14 00:23:22', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290732', '1', '2025-02-14 00:22:53', '2025-02-14 00:22:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290728', '1', '2025-02-14 00:22:20', '2025-02-14 00:22:18', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290727', '1', '2025-02-14 00:22:17', '2025-02-14 00:22:15', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290724', '1', '2025-02-14 00:21:46', '2025-02-14 00:21:44', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290721', '1', '2025-02-14 00:21:15', '2025-02-14 00:21:13', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290720', '1', '2025-02-14 00:21:10', '2025-02-14 00:21:08', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290717', '1', '2025-02-14 00:20:39', '2025-02-14 00:20:37', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290716', '1', '2025-02-14 00:20:34', '2025-02-14 00:20:32', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290713', '1', '2025-02-14 00:20:02', '2025-02-14 00:20:00', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290712', '1', '2025-02-14 00:20:00', '2025-02-14 00:19:58', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290709', '1', '2025-02-14 00:19:29', '2025-02-14 00:19:27', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290705', '1', '2025-02-14 00:18:56', '2025-02-14 00:18:54', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290704', '1', '2025-02-14 00:18:48', '2025-02-14 00:18:46', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290701', '1', '2025-02-14 00:18:17', '2025-02-14 00:18:15', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290700', '1', '2025-02-14 00:18:12', '2025-02-14 00:18:10', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290697', '1', '2025-02-14 00:17:41', '2025-02-14 00:17:39', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290693', '1', '2025-02-14 00:17:08', '2025-02-14 00:17:06', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290692', '1', '2025-02-14 00:17:06', '2025-02-14 00:17:03', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290689', '1', '2025-02-14 00:16:34', '2025-02-14 00:16:32', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290685', '1', '2025-02-14 00:16:01', '2025-02-14 00:15:59', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290682', '1', '2025-02-14 00:15:30', '2025-02-14 00:15:28', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290676', '1', '2025-02-14 00:09:52', '2025-02-14 00:09:50', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290673', '1', '2025-02-14 00:09:21', '2025-02-14 00:09:19', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290672', '1', '2025-02-14 00:09:19', '2025-02-14 00:09:17', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290669', '1', '2025-02-14 00:08:48', '2025-02-14 00:08:46', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290661', '1', '2025-02-14 00:00:53', '2025-02-14 00:00:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290658', '1', '2025-02-14 00:00:22', '2025-02-14 00:00:19', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290654', '1', '2025-02-13 23:59:45', '2025-02-13 23:59:43', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290650', '1', '2025-02-13 23:59:12', '2025-02-13 23:59:10', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290649', '1', '2025-02-13 23:59:08', '2025-02-13 23:59:06', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290646', '1', '2025-02-13 23:58:37', '2025-02-13 23:58:35', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290645', '1', '2025-02-13 23:58:28', '2025-02-13 23:58:26', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290642', '1', '2025-02-13 23:57:57', '2025-02-13 23:57:55', '[{\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290641', '1', '2025-02-13 23:57:55', '2025-02-13 23:57:53', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290638', '1', '2025-02-13 23:57:24', '2025-02-13 23:57:22', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290637', '1', '2025-02-13 23:57:22', '2025-02-13 23:57:20', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290634', '1', '2025-02-13 23:56:51', '2025-02-13 23:56:49', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290633', '1', '2025-02-13 23:56:47', '2025-02-13 23:56:45', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290630', '1', '2025-02-13 23:56:15', '2025-02-13 23:56:13', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290629', '1', '2025-02-13 23:56:10', '2025-02-13 23:56:08', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290626', '1', '2025-02-13 23:55:39', '2025-02-13 23:55:37', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290625', '1', '2025-02-13 23:55:30', '2025-02-13 23:55:28', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290622', '1', '2025-02-13 23:54:59', '2025-02-13 23:54:57', '[{\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290621', '1', '2025-02-13 23:54:57', '2025-02-13 23:54:55', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290618', '1', '2025-02-13 23:54:26', '2025-02-13 23:54:24', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290617', '1', '2025-02-13 23:54:23', '2025-02-13 23:54:21', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290614', '1', '2025-02-13 23:53:52', '2025-02-13 23:53:50', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290613', '1', '2025-02-13 23:53:41', '2025-02-13 23:53:39', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290610', '1', '2025-02-13 23:53:09', '2025-02-13 23:53:07', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290441', '1', '2025-02-13 21:04:20', '2025-02-13 21:04:18', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290438', '1', '2025-02-13 21:03:49', '2025-02-13 21:03:47', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290431', '1', '2025-02-13 21:02:44', '2025-02-13 21:02:42', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290427', '1', '2025-02-13 21:02:04', '2025-02-13 21:02:02', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290423', '1', '2025-02-13 21:01:31', '2025-02-13 21:01:29', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290419', '1', '2025-02-13 21:00:56', '2025-02-13 21:00:54', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290418', '1', '2025-02-13 21:00:46', '2025-02-13 21:00:44', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290415', '1', '2025-02-13 21:00:15', '2025-02-13 21:00:13', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290414', '1', '2025-02-13 21:00:06', '2025-02-13 21:00:04', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290411', '1', '2025-02-13 20:59:35', '2025-02-13 20:59:33', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290407', '1', '2025-02-13 20:59:02', '2025-02-13 20:59:00', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290406', '1', '2025-02-13 20:58:54', '2025-02-13 20:58:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290403', '1', '2025-02-13 20:58:22', '2025-02-13 20:58:20', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290399', '1', '2025-02-13 20:57:48', '2025-02-13 20:57:46', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290398', '1', '2025-02-13 20:57:41', '2025-02-13 20:57:39', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290395', '1', '2025-02-13 20:57:10', '2025-02-13 20:57:08', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290394', '1', '2025-02-13 20:57:06', '2025-02-13 20:57:04', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290390', '1', '2025-02-13 20:56:32', '2025-02-13 20:56:30', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290387', '1', '2025-02-13 20:56:01', '2025-02-13 20:55:59', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290386', '1', '2025-02-13 20:55:59', '2025-02-13 20:55:57', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290383', '1', '2025-02-13 20:55:28', '2025-02-13 20:55:26', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290382', '1', '2025-02-13 20:55:26', '2025-02-13 20:55:24', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290379', '1', '2025-02-13 20:54:55', '2025-02-13 20:54:53', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290378', '1', '2025-02-13 20:54:44', '2025-02-13 20:54:42', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290375', '1', '2025-02-13 20:54:13', '2025-02-13 20:54:11', '[{\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290374', '1', '2025-02-13 20:54:11', '2025-02-13 20:54:09', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290371', '1', '2025-02-13 20:53:40', '2025-02-13 20:53:38', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290370', '1', '2025-02-13 20:53:37', '2025-02-13 20:53:34', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290363', '1', '2025-02-13 20:52:32', '2025-02-13 20:52:30', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290299', '1', '2025-02-13 19:48:43', '2025-02-13 19:48:41', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290296', '1', '2025-02-13 19:48:12', '2025-02-13 19:48:10', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290295', '1', '2025-02-13 19:48:07', '2025-02-13 19:48:05', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290292', '1', '2025-02-13 19:47:36', '2025-02-13 19:47:34', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290291', '1', '2025-02-13 19:47:34', '2025-02-13 19:47:32', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290288', '1', '2025-02-13 19:47:03', '2025-02-13 19:47:01', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290287', '1', '2025-02-13 19:46:59', '2025-02-13 19:46:56', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290280', '1', '2025-02-13 19:45:54', '2025-02-13 19:45:52', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290229', '1', '2025-02-13 18:55:16', '2025-02-13 18:55:14', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290226', '1', '2025-02-13 18:54:45', '2025-02-13 18:54:43', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290225', '1', '2025-02-13 18:54:43', '2025-02-13 18:54:41', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290222', '1', '2025-02-13 18:54:12', '2025-02-13 18:54:10', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290221', '1', '2025-02-13 18:53:52', '2025-02-13 18:53:50', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290218', '1', '2025-02-13 18:53:21', '2025-02-13 18:53:19', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290089', '1', '2025-02-13 16:44:59', '2025-02-13 16:44:57', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290086', '1', '2025-02-13 16:44:28', '2025-02-13 16:44:26', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290085', '1', '2025-02-13 16:44:19', '2025-02-13 16:44:17', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290082', '1', '2025-02-13 16:43:48', '2025-02-13 16:43:45', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290078', '1', '2025-02-13 16:43:14', '2025-02-13 16:43:12', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290074', '1', '2025-02-13 16:42:40', '2025-02-13 16:42:38', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290073', '1', '2025-02-13 16:42:29', '2025-02-13 16:42:27', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290070', '1', '2025-02-13 16:41:58', '2025-02-13 16:41:56', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290069', '1', '2025-02-13 16:41:55', '2025-02-13 16:41:53', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290066', '1', '2025-02-13 16:41:24', '2025-02-13 16:41:22', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290063', '1', '2025-02-13 16:40:53', '2025-02-13 16:40:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290062', '1', '2025-02-13 16:40:49', '2025-02-13 16:40:47', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290058', '1', '2025-02-13 16:40:16', '2025-02-13 16:40:13', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290055', '1', '2025-02-13 16:39:44', '2025-02-13 16:39:42', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290054', '1', '2025-02-13 16:39:41', '2025-02-13 16:39:39', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290048', '1', '2025-02-13 16:38:39', '2025-02-13 16:38:37', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290047', '1', '2025-02-13 16:38:37', '2025-02-13 16:38:35', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290044', '1', '2025-02-13 16:38:06', '2025-02-13 16:38:04', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290043', '1', '2025-02-13 16:37:58', '2025-02-13 16:37:56', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290040', '1', '2025-02-13 16:37:27', '2025-02-13 16:37:25', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290039', '1', '2025-02-13 16:37:25', '2025-02-13 16:37:23', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290036', '1', '2025-02-13 16:36:54', '2025-02-13 16:36:52', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290028', '1', '2025-02-13 16:35:46', '2025-02-13 16:35:44', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290027', '1', '2025-02-13 16:35:36', '2025-02-13 16:35:34', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290024', '1', '2025-02-13 16:35:05', '2025-02-13 16:35:03', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290023', '1', '2025-02-13 16:35:00', '2025-02-13 16:34:58', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290020', '1', '2025-02-13 16:34:29', '2025-02-13 16:34:27', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290019', '1', '2025-02-13 16:34:26', '2025-02-13 16:34:24', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['290016', '1', '2025-02-13 16:33:55', '2025-02-13 16:33:53', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289835', '1', '2025-02-13 13:32:33', '2025-02-13 13:32:31', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289832', '1', '2025-02-13 13:32:02', '2025-02-13 13:31:59', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289831', '1', '2025-02-13 13:31:25', '2025-02-13 13:31:23', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289828', '1', '2025-02-13 13:30:54', '2025-02-13 13:30:52', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289827', '1', '2025-02-13 13:30:52', '2025-02-13 13:30:50', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289824', '1', '2025-02-13 13:30:21', '2025-02-13 13:30:19', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289823', '1', '2025-02-13 13:30:16', '2025-02-13 13:30:14', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289820', '1', '2025-02-13 13:29:45', '2025-02-13 13:29:43', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289819', '1', '2025-02-13 13:29:41', '2025-02-13 13:29:39', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289816', '1', '2025-02-13 13:29:10', '2025-02-13 13:29:08', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289815', '1', '2025-02-13 13:29:03', '2025-02-13 13:29:01', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289812', '1', '2025-02-13 13:28:32', '2025-02-13 13:28:30', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289811', '1', '2025-02-13 13:28:30', '2025-02-13 13:28:27', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289808', '1', '2025-02-13 13:27:58', '2025-02-13 13:27:56', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289807', '1', '2025-02-13 13:27:38', '2025-02-13 13:27:36', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289804', '1', '2025-02-13 13:27:07', '2025-02-13 13:27:05', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289749', '1', '2025-02-13 12:34:53', '2025-02-13 12:34:51', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289745', '1', '2025-02-13 12:34:20', '2025-02-13 12:34:18', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289741', '1', '2025-02-13 12:33:44', '2025-02-13 12:33:42', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289737', '1', '2025-02-13 12:33:11', '2025-02-13 12:33:09', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289736', '1', '2025-02-13 12:33:06', '2025-02-13 12:33:04', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289733', '1', '2025-02-13 12:32:35', '2025-02-13 12:32:33', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289729', '1', '2025-02-13 12:32:02', '2025-02-13 12:32:00', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289728', '1', '2025-02-13 12:31:57', '2025-02-13 12:31:54', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289725', '1', '2025-02-13 12:31:25', '2025-02-13 12:31:23', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289721', '1', '2025-02-13 12:30:52', '2025-02-13 12:30:50', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289720', '1', '2025-02-13 12:30:47', '2025-02-13 12:30:45', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289717', '1', '2025-02-13 12:30:16', '2025-02-13 12:30:14', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289713', '1', '2025-02-13 12:29:43', '2025-02-13 12:29:41', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289712', '1', '2025-02-13 12:29:38', '2025-02-13 12:29:36', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289709', '1', '2025-02-13 12:29:07', '2025-02-13 12:29:05', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289705', '1', '2025-02-13 12:28:34', '2025-02-13 12:28:31', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289704', '1', '2025-02-13 12:28:28', '2025-02-13 12:28:26', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289701', '1', '2025-02-13 12:27:57', '2025-02-13 12:27:55', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289697', '1', '2025-02-13 12:27:24', '2025-02-13 12:27:22', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289693', '1', '2025-02-13 12:26:50', '2025-02-13 12:26:48', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289692', '1', '2025-02-13 12:26:46', '2025-02-13 12:26:44', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289689', '1', '2025-02-13 12:26:15', '2025-02-13 12:26:13', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289685', '1', '2025-02-13 12:25:41', '2025-02-13 12:25:39', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289684', '1', '2025-02-13 12:25:37', '2025-02-13 12:25:34', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 8, \"light_len\": 8, \"triggered\": true}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289681', '1', '2025-02-13 12:25:05', '2025-02-13 12:25:03', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289680', '1', '2025-02-13 12:25:00', '2025-02-13 12:24:58', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289677', '1', '2025-02-13 12:24:29', '2025-02-13 12:24:27', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289673', '1', '2025-02-13 12:23:56', '2025-02-13 12:23:54', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289669', '1', '2025-02-13 12:23:22', '2025-02-13 12:23:20', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289665', '1', '2025-02-13 12:22:48', '2025-02-13 12:22:46', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289664', '1', '2025-02-13 12:22:42', '2025-02-13 12:22:40', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289661', '1', '2025-02-13 12:22:11', '2025-02-13 12:22:08', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289657', '1', '2025-02-13 12:21:37', '2025-02-13 12:21:35', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289656', '1', '2025-02-13 12:21:34', '2025-02-13 12:21:32', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289653', '1', '2025-02-13 12:21:03', '2025-02-13 12:21:01', '[{\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289652', '1', '2025-02-13 12:21:00', '2025-02-13 12:20:58', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289649', '1', '2025-02-13 12:20:29', '2025-02-13 12:20:27', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289648', '1', '2025-02-13 12:20:23', '2025-02-13 12:20:21', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289645', '1', '2025-02-13 12:19:52', '2025-02-13 12:19:50', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289644', '1', '2025-02-13 12:19:50', '2025-02-13 12:19:48', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289641', '1', '2025-02-13 12:19:19', '2025-02-13 12:19:17', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289640', '1', '2025-02-13 12:19:16', '2025-02-13 12:19:13', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289637', '1', '2025-02-13 12:18:44', '2025-02-13 12:18:42', '[{\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289636', '1', '2025-02-13 12:18:41', '2025-02-13 12:18:39', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289633', '1', '2025-02-13 12:18:10', '2025-02-13 12:18:08', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289632', '1', '2025-02-13 12:18:04', '2025-02-13 12:18:02', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289629', '1', '2025-02-13 12:17:33', '2025-02-13 12:17:31', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289628', '1', '2025-02-13 12:17:31', '2025-02-13 12:17:29', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289625', '1', '2025-02-13 12:17:00', '2025-02-13 12:16:58', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289624', '1', '2025-02-13 12:16:58', '2025-02-13 12:16:56', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289621', '1', '2025-02-13 12:16:27', '2025-02-13 12:16:25', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289620', '1', '2025-02-13 12:16:24', '2025-02-13 12:16:22', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289617', '1', '2025-02-13 12:15:53', '2025-02-13 12:15:50', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289616', '1', '2025-02-13 12:15:45', '2025-02-13 12:15:43', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289613', '1', '2025-02-13 12:15:14', '2025-02-13 12:15:12', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289612', '1', '2025-02-13 12:15:11', '2025-02-13 12:15:09', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289609', '1', '2025-02-13 12:14:40', '2025-02-13 12:14:38', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289606', '1', '2025-02-13 12:14:09', '2025-02-13 12:14:07', '[{\"freq\": 433, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289605', '1', '2025-02-13 12:14:05', '2025-02-13 12:14:03', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['289602', '1', '2025-02-13 12:13:34', '2025-02-13 12:13:32', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 868, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "['287824', '1', '2025-02-12 04:41:04', '2025-02-12 04:41:02', '[{\"freq\": 433, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 700, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 868, \"amplitude\": 9, \"triggered\": true}, {\"freq\": 915, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 1200, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 2400, \"amplitude\": 0, \"light_len\": 0, \"triggered\": false}, {\"freq\": 5200, \"amplitude\": 0, \"triggered\": false}, {\"freq\": 5800, \"amplitude\": 0, \"triggered\": false}]', 'NULL', 'freq']\n",
+      "Данные успешно обработаны и сохранены в History_change_1.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "import csv\n",
+    "\n",
+    "# Путь к входному CSV-файлу\n",
+    "input_file = 'History_1.csv'\n",
+    "\n",
+    "# Путь к выходному CSV-файлу (с правильно разделёнными данными)\n",
+    "output_file = 'History_change_1.csv'\n",
+    "\n",
+    "# Открываем исходный файл для чтения и новый файл для записи\n",
+    "with open(input_file, mode='r', encoding='utf-8') as infile:\n",
+    "    with open(output_file, mode='w', encoding='utf-8-sig', newline='') as outfile:\n",
+    "\n",
+    "        # Создаем объект reader для чтения CSV с учетом кавычек\n",
+    "        reader = csv.reader(infile, delimiter=',', quotechar='\"')\n",
+    "\n",
+    "        # Создаем объект writer для записи в новый CSV-файл\n",
+    "        writer = csv.writer(outfile, delimiter=';', quotechar=\"'\", quoting=csv.QUOTE_MINIMAL)\n",
+    "\n",
+    "        # Проходимся по каждой строке в исходном файле\n",
+    "        for row in reader:\n",
+    "            # Записываем строку в выходной файл\n",
+    "            print(row)\n",
+    "            writer.writerow(row)\n",
+    "\n",
+    "print(f\"Данные успешно обработаны и сохранены в {output_file}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "caf7679f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "97cfbd11",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/config_ensemble.yaml

@@ -1,5 +1,5 @@
 # Training params
-epoch : 5
+epoch : 10
 batch_size : 4
 num_workers: 8
 limit : 5
@@ -16,5 +16,5 @@ loss_function :
 # Scheduler
 scheduler :
   name : torch.optim.lr_scheduler.StepLR
-  gamma : 0.15
-  step_size : 3
+  gamma : 0.01
+  step_size : 10

train_scripts/create_dataset_overlay.py

@@ -0,0 +1,217 @@
+#!/usr/bin/env python3
+import argparse
+import csv
+import os
+import random
+import shutil
+from pathlib import Path
+
+import cv2
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+import numpy as np
+from tqdm import tqdm
+
+
+DEFAULT_FREQS = (1200, 2400)
+PNG_SUFFIXES = ("_real.png", "_imag.png", "_spec.png")
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description=(
+            "Build a two-class image dataset with drone signatures overlaid on noise images. "
+            "The output is ready for Training_models2pic_val_loss.ipynb."
+        )
+    )
+    parser.add_argument("--drone-root", default="/mnt/data/Dataset/drone")
+    parser.add_argument("--noise-img-root", default="/mnt/data/Dataset_img/noise")
+    parser.add_argument("--output-root", default="/mnt/data/Dataset_overlay")
+    parser.add_argument("--freqs", default=",".join(str(v) for v in DEFAULT_FREQS))
+    parser.add_argument("--alpha", type=float, default=1.0, help="Overlay strength: 1.0 keeps the darkest drone/noise pixels.")
+    parser.add_argument("--limit-per-freq", type=int, default=0, help="0 means use all available noise images per frequency.")
+    parser.add_argument("--seed", type=int, default=42)
+    parser.add_argument("--copy-noise", action="store_true", help="Copy noise files instead of hardlinking them.")
+    parser.add_argument("--overwrite", action="store_true")
+    parser.add_argument("--dry-run", action="store_true")
+    parser.add_argument("--no-progress", action="store_true", help="Disable tqdm progress bars.")
+    return parser.parse_args()
+
+
+def parse_freqs(value):
+    return [int(item.strip()) for item in value.split(",") if item.strip()]
+
+
+def collect_drone_npys(root, freq):
+    root = Path(root)
+    candidates = []
+    candidates.extend((root / str(freq)).rglob("*.npy"))
+    candidates.extend((root / f"{freq}_jpg").glob("*.npy"))
+    return sorted({p for p in candidates if p.is_file()})
+
+
+def collect_noise_npys(root, freq):
+    root = Path(root)
+    candidates = []
+    candidates.extend((root / f"{freq}_jpg").glob("*.npy"))
+    candidates.extend((root / str(freq)).rglob("*.npy"))
+    return sorted({p for p in candidates if p.is_file()})
+
+
+def load_image_tensor(path):
+    arr = np.load(path)
+    if arr.ndim == 2:
+        arr = np.stack([arr, arr, arr], axis=0)
+    if arr.ndim == 3 and arr.shape[-1] in (1, 3) and arr.shape[0] not in (1, 3):
+        arr = np.moveaxis(arr, -1, 0)
+    if arr.ndim != 3:
+        raise ValueError(f"expected 3D image tensor, got shape={arr.shape} path={path}")
+    if arr.shape[0] == 1:
+        arr = np.repeat(arr, 3, axis=0)
+    if arr.shape[0] < 3:
+        raise ValueError(f"expected at least 3 channels, got shape={arr.shape} path={path}")
+    return arr[:3].astype(np.float32, copy=False)
+
+
+def resize_like(arr, shape):
+    if arr.shape == shape:
+        return arr
+    channels, height, width = shape
+    resized = []
+    for channel in arr[:channels]:
+        resized.append(cv2.resize(channel, (width, height), interpolation=cv2.INTER_LINEAR))
+    return np.asarray(resized, dtype=np.float32)
+
+
+def overlay_tensors(noise, drone, alpha):
+    drone = resize_like(drone, noise.shape)
+    bright_overlay = np.minimum(noise, drone)
+    mixed = (1.0 - alpha) * noise + alpha * bright_overlay
+    return np.clip(mixed, 0, 255).astype(np.float32)
+
+
+def to_uint8(channel):
+    arr = np.asarray(channel, dtype=np.float32)
+    finite = arr[np.isfinite(arr)]
+    if finite.size == 0:
+        return np.zeros(arr.shape, dtype=np.uint8)
+    min_v = float(finite.min())
+    max_v = float(finite.max())
+    if min_v >= 0.0 and max_v <= 255.0:
+        return np.clip(arr, 0, 255).astype(np.uint8)
+    if max_v == min_v:
+        return np.zeros(arr.shape, dtype=np.uint8)
+    norm = (arr - min_v) / (max_v - min_v)
+    return np.clip(norm * 255.0, 0, 255).astype(np.uint8)
+
+
+def save_notebook_style_png(path, channel):
+    fig = plt.figure(figsize=(16, 16))
+    plt.imshow(channel)
+    plt.savefig(path)
+    plt.clf()
+    plt.cla()
+    plt.close()
+    plt.close(fig)
+
+
+def save_sample(base_path, tensor):
+    np.save(str(base_path) + ".npy", tensor.astype(np.float32))
+    for idx, suffix in enumerate(PNG_SUFFIXES):
+        save_notebook_style_png(str(base_path) + suffix, tensor[idx])
+
+
+def link_or_copy(src, dst, copy_file):
+    dst.parent.mkdir(parents=True, exist_ok=True)
+    if dst.exists():
+        return
+    if copy_file:
+        shutil.copy2(src, dst)
+        return
+    try:
+        os.link(src, dst)
+    except OSError:
+        shutil.copy2(src, dst)
+
+
+def copy_noise_family(noise_npy, out_dir, copy_file):
+    base_name = noise_npy.name[:-4] if noise_npy.name.endswith(".npy") else noise_npy.name
+    link_or_copy(noise_npy, out_dir / noise_npy.name, copy_file)
+    for suffix in PNG_SUFFIXES:
+        sidecar = noise_npy.with_name(base_name + suffix)
+        if sidecar.exists():
+            link_or_copy(sidecar, out_dir / sidecar.name, copy_file)
+
+
+def main():
+    args = parse_args()
+    random.seed(args.seed)
+    freqs = parse_freqs(args.freqs)
+    output_root = Path(args.output_root)
+    manifest_rows = []
+
+    if args.overwrite and output_root.exists() and not args.dry_run:
+        shutil.rmtree(output_root)
+
+    for freq in freqs:
+        drone_files = collect_drone_npys(args.drone_root, freq)
+        noise_files = collect_noise_npys(args.noise_img_root, freq)
+        if not drone_files:
+            raise RuntimeError(f"no drone npy files found for freq={freq} under {args.drone_root}")
+        if not noise_files:
+            raise RuntimeError(f"no noise image npy files found for freq={freq} under {args.noise_img_root}")
+
+        count = len(noise_files) if args.limit_per_freq <= 0 else min(args.limit_per_freq, len(noise_files))
+        selected_noise = noise_files[:]
+        random.shuffle(selected_noise)
+        selected_noise = selected_noise[:count]
+
+        out_drone_dir = output_root / "drone" / f"{freq}_jpg"
+        out_noise_dir = output_root / "noise" / f"{freq}_jpg"
+
+        print(f"freq={freq}: drone_source={len(drone_files)} noise_source={len(noise_files)} output_per_class={count}")
+        if args.dry_run:
+            continue
+
+        out_drone_dir.mkdir(parents=True, exist_ok=True)
+        out_noise_dir.mkdir(parents=True, exist_ok=True)
+
+        iterator = tqdm(
+            enumerate(selected_noise),
+            total=count,
+            desc=f"overlay freq={freq}",
+            unit="sample",
+            disable=args.no_progress,
+        )
+        for idx, noise_path in iterator:
+            drone_path = drone_files[idx % len(drone_files)]
+            noise_tensor = load_image_tensor(noise_path)
+            drone_tensor = load_image_tensor(drone_path)
+            mixed = overlay_tensors(noise_tensor, drone_tensor, args.alpha)
+
+            out_base = out_drone_dir / f"overlay_{freq}_{idx:06d}"
+            save_sample(out_base, mixed)
+            copy_noise_family(noise_path, out_noise_dir, args.copy_noise)
+
+            manifest_rows.append({
+                "freq": freq,
+                "output": str(out_base) + ".npy",
+                "noise_source": str(noise_path),
+                "drone_source": str(drone_path),
+                "alpha": args.alpha,
+            })
+
+    if not args.dry_run:
+        manifest_path = output_root / "overlay_manifest.csv"
+        with manifest_path.open("w", newline="", encoding="utf-8") as fh:
+            writer = csv.DictWriter(fh, fieldnames=["freq", "output", "noise_source", "drone_source", "alpha"])
+            writer.writeheader()
+            writer.writerows(manifest_rows)
+        print(f"wrote {len(manifest_rows)} overlay samples")
+        print(f"manifest: {manifest_path}")
+        print(f"dataset: {output_root}")
+
+
+if __name__ == "__main__":
+    main()

train_scripts/my_csv_make.ipynb

@@ -0,0 +1,58 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "537ea5d0-1d6c-423e-9417-171b70a76c66",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "\n",
+    "path = '//192.168.11.63/data/DATASETS/Energomash/915_learning'\n",
+    "pd_columns = ['file_name']\n",
+    "df = pd.DataFrame(columns=pd_columns)\n",
+    "\n",
+    "p = 0\n",
+    "for i in os.walk(path):\n",
+    "    p+=1\n",
+    "    if p != 1:\n",
+    "        for j in i[2]:\n",
+    "            row = pd.DataFrame({pd_columns[0]: [str(str(i[0]) + '\\\\' + str(j)).replace('\\\\', '/')]})\n",
+    "            df = pd.concat([df, row], ignore_index=True)\n",
+    "\n",
+    "df.to_csv(path + '\\dataset.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8f6e1ff8",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/triangulation_accurate.ipynb

@@ -0,0 +1,91 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "689613d2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "80.58750000000002\n",
+      "(array([8.97705408, 4.95      , 0.        ]), array([-8.97705408,  4.95      ,  0.        ]))\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy  \n",
+    "from math import sqrt as square\n",
+    "from numpy import sqrt, dot, cross                       \n",
+    "from numpy.linalg import norm  \n",
+    "\n",
+    "#rssi = [rssi, max_rssi, min_rssi, gamma]\n",
+    "\n",
+    "def dist(rssi):\n",
+    "    rssi = list(map(float, rssi))\n",
+    "    return square(abs(rssi[0]-rssi[1]))*rssi[3]/square(abs(rssi[0]-rssi[2]))\n",
+    "\n",
+    "def sol(x1,x2,x3,rssi1,rssi2,rssi3):\n",
+    "    r1 = dist(rssi1)\n",
+    "    r2 = dist(rssi2)\n",
+    "    r3 = dist(rssi3)\n",
+    "    x1=numpy.array(x1)\n",
+    "    x2=numpy.array(x2)\n",
+    "    x3=numpy.array(x3)\n",
+    "    temp1 = x2-x1                                        \n",
+    "    e_x = temp1/norm(temp1)                              \n",
+    "    temp2 = x3-x1                                        \n",
+    "    i = dot(e_x,temp2)                                   \n",
+    "    temp3 = temp2 - i*e_x                                \n",
+    "    e_y = temp3/norm(temp3)                              \n",
+    "    e_z = cross(e_x,e_y)                                 \n",
+    "    d = norm(x2-x1)                                      \n",
+    "    j = dot(e_y,temp2)                                   \n",
+    "    x = (r1*r1 - r2*r2 + d*d) / (2*d)                    \n",
+    "    y = (r1*r1 - r3*r3 -2*i*x + i*i + j*j) / (2*j)       \n",
+    "    temp4 = r1*r1 - x*x - y*y \n",
+    "    print(temp4)\n",
+    "    if temp4<0:                                          \n",
+    "        return \"Нет пересечения!\"\n",
+    "    z = sqrt(temp4)                                      \n",
+    "    p_12_a = x1 + x*e_x + y*e_y + z*e_z                  \n",
+    "    p_12_b = x1 + x*e_x + y*e_y - z*e_z                  \n",
+    "    return p_12_a,p_12_b\n",
+    "\n",
+    "\n",
+    "print(sol([0,0,1],[0,0,-1],[0,10,0],[50,100,0,10.3],[50,100,0,10.3],[50,100,0,10.3]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0a68f35a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

train_scripts/triangulation_direction_2D.ipynb

@@ -0,0 +1,57 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f18afe4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy  \n",
+    "from math import sqrt as square\n",
+    "from numpy import sqrt, dot, cross                       \n",
+    "from numpy.linalg import norm  \n",
+    "\n",
+    "#rssi = [rssi, max_rssi, min_rssi, gamma]\n",
+    "\n",
+    "def dist(rssi):\n",
+    "    rssi = list(map(float, rssi))\n",
+    "    return square(abs(rssi[0]-rssi[1]))*rssi[3]/square(abs(rssi[0]-rssi[2]))\n",
+    "\n",
+    "def sol(x1,x2,x3,rssi1,rssi2,rssi3):\n",
+    "    r1 = dist(rssi1)\n",
+    "    r2 = dist(rssi2)\n",
+    "    r3 = dist(rssi3)\n",
+    "    x1=numpy.array(x1)\n",
+    "    x2=numpy.array(x2)\n",
+    "    x3=numpy.array(x3)\n",
+    "    \n",
+    "    return sector.\n",
+    "\n",
+    "\n",
+    "print(sol([0,0,1],[0,0,-1],[0,10,0],[50,100,0,10.3],[50,100,0,10.3],[50,100,0,10.3]))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}