1.前言：.Halcon的深度学习标注工具一直在更新，我下载的20.11版本的Deep Learning Tool已经显示过期，无奈只能下载最新版MVTec Deep Learning Tool 24.05。不过最新版的标注工具做的很人性化，分类，目标检测，分割，异常值检测，OCR全都有,有兴趣的小伙伴可以下载来试试，可以在工具UI界面实现标注，训练加测试，很好用。如果想自己用代码实现训练也可以，先用标注工具把所有的图标注完毕后，导出标注数据集，即可利用此数据集，在halcon代码中训练。

2.上干货，深度目标检测训练源码：
模型训练预处理准备阶段************
dev_update_off ()

• 选择预处理模型.
  Backbone := ‘pretrained_dl_classifier_compact.hdl’
  *检测种类数
  NumClasses := 6
• Image dimensions of the network. Later, these values are
• used to rescale the images during preprocessing.
  ImageWidth := 512
  ImageHeight := 320
  ImageNumChannels := 3

*将容量设置为“中等”，这足以完成此任务
*并提供更好的推理和训练速度。与
*“高”，“中”型号的速度是“中”的两倍多，
*同时显示出几乎相同的检测性能。
Capacity := ‘medium’
*

• 分割数据集的百分比。
  TrainingPercent := 70
  ValidationPercent := 15
• In order to get a reproducible split we set a random seed.
• This means that rerunning the script results in the same split of DLDataset.
  SeedRand := 42

---

• ** Set input and output paths ***

---

• All example data is written to this folder.
  ExampleDataDir := ‘E:/2024-4-10’

• Path to the image directory.
  HalconImageDir := ExampleDataDir + ‘/images/’

• Write the initialized DL object detection model to train it in example part 2.
  DLModelFileName := ExampleDataDir + ‘/pretrained_dl_model_detection.hdl’

• Dataset directory for any outputs written by preprocess_dl_dataset.
  DataDirectory := ExampleDataDir + ‘/dldataset_pcb_’ + ImageWidth + ‘x’ + ImageHeight

• Store preprocess parameters separately in order to use it e.g. during inference.
  PreprocessParamFileName := DataDirectory + ‘/dl_preprocess_param.hdict’
  *标注数据集路径
  DataDirectPath:=ExampleDataDir + ‘/Pcb.hdict’

• Output path of the best evaluated model.
  BestModelBaseName := ExampleDataDir + ‘/best_dl_model_detection’

• Output path for the final trained model.
  FinalModelBaseName := ExampleDataDir + ‘/final_dl_model_detection’
  InitialModelFileName := ExampleDataDir + ‘/pretrained_dl_model_detection.hdl’
  DLDatasetFileName := DataDirectory + ‘/dl_dataset.hdict’

---

• ** Read the labeled dataset and split the dataset ***

---

• In order to get reproducible results we set a seed here.
  set_system (‘seed_rand’, SeedRand)
• Create the output directory if it does not exist yet.
  file_exists (ExampleDataDir, FileExists)
  if (not FileExists)
  make_dir (ExampleDataDir)
  endif
• Read in a DLDataset.
  read_dict (DataDirectPath, [], [], DLDataset)
• Split the dataset into train/validation and test.
  split_dl_dataset (DLDataset, TrainingPercent, ValidationPercent, [])

---

• ** Determine model parameters from data ***

---

• Generate model parameters min_level, max_level, anchor_num_subscales,
• and anchor_aspect_ratios from the dataset in order to improve the
• training result. Please note that optimizing the model parameters too
• much on the training data can lead to overfitting. Hence, this should
• only be done if the actual application data are similar to the training
• data.
  create_dict (GenParam)
  set_dict_tuple (GenParam, ‘split’, ‘train’)

determine_dl_model_detection_param (DLDataset, ImageWidth, ImageHeight, GenParam, DLDetectionModelParam)
*

• Get the generated model parameters.
  get_dict_tuple (DLDetectionModelParam, ‘min_level’, MinLevel)
  get_dict_tuple (DLDetectionModelParam, ‘max_level’, MaxLevel)
  get_dict_tuple (DLDetectionModelParam, ‘anchor_num_subscales’, AnchorNumSubscales)
  get_dict_tuple (DLDetectionModelParam, ‘anchor_aspect_ratios’, AnchorAspectRatios)

---

• ** Create the object detection model ***

---

• Create dictionary for generic parameters and create the object detection model.
  create_dict (DLModelDetectionParam)
  set_dict_tuple (DLModelDetectionParam, ‘image_width’, ImageWidth)
  set_dict_tuple (DLModelDetectionParam, ‘image_height’, ImageHeight)
  set_dict_tuple (DLModelDetectionParam, ‘image_num_channels’, ImageNumChannels)
  set_dict_tuple (DLModelDetectionParam, ‘min_level’, MinLevel)
  set_dict_tuple (DLModelDetectionParam, ‘max_level’, MaxLevel)
  set_dict_tuple (DLModelDetectionParam, ‘anchor_num_subscales’, AnchorNumSubscales)
  set_dict_tuple (DLModelDetectionParam, ‘anchor_aspect_ratios’, AnchorAspectRatios)
  set_dict_tuple (DLModelDetectionParam, ‘capacity’, Capacity)
• Get class IDs from dataset for the model.
  get_dict_tuple (DLDataset, ‘class_ids’, ClassIDs)
  set_dict_tuple (DLModelDetectionParam, ‘class_ids’, ClassIDs)
• Create the model.
  create_dl_model_detection (Backbone, NumClasses, DLModelDetectionParam, DLModelHandle)
• Write the initialized DL object detection model
• to train it later in part 2.
  write_dl_model (DLModelHandle, DLModelFileName)

---

• ** Preprocess the dataset ***

---

• Get preprocessing parameters from model.
  create_dl_preprocess_param_from_model (DLModelHandle, ‘none’, ‘full_domain’, [], [], [], DLPreprocessParam)
• Preprocess the dataset. This might take a few minutes.
  create_dict (GenParam)
  set_dict_tuple (GenParam, ‘overwrite_files’, true)
  preprocess_dl_dataset (DLDataset, DataDirectory, DLPreprocessParam, GenParam, DLDatasetFilename)
• Write preprocessing parameters to use them in later parts.
  write_dict (DLPreprocessParam, PreprocessParamFileName, [], [])

---

• ** Preview the preprocessed dataset ***

---

• Before moving on to training, it is recommended to check the preprocessed dataset.
• Display the DLSamples for 10 randomly selected train images.
  get_dict_tuple (DLDataset, ‘samples’, DatasetSamples)
  find_dl_samples (DatasetSamples, ‘split’, ‘train’, ‘match’, SampleIndices)
  tuple_shuffle (SampleIndices, ShuffledIndices)
  *训练的数据种类是6，所以下面算子设置[0:5]
  read_dl_samples (DLDataset, ShuffledIndices[0:5], DLSampleBatchDisplay)
• Set parameters for dev_display_dl_data.
  create_dict (WindowHandleDict)
  create_dict (GenParam)
  set_dict_tuple (GenParam, ‘scale_windows’, 1.2)
• Display the samples in DLSampleBatchDisplay.
  for Index := 0 to |DLSampleBatchDisplay| - 1 by 1
  *
  • Loop over samples in DLSampleBatchDisplay.
    dev_display_dl_data (DLSampleBatchDisplay[Index], [], DLDataset, ‘bbox_ground_truth’, GenParam, WindowHandleDict)
    get_dict_tuple (WindowHandleDict, ‘bbox_ground_truth’, WindowHandles)
  • Add explanatory text.
    dev_set_window (WindowHandles[0])
    get_dict_object (Image, DLSampleBatchDisplay[Index], ‘image’)
    get_image_size (Image, ImageWidth, ImageHeight)
    dev_disp_text ('New image size after preprocessing: ’ + ImageWidth + ’ x ’ + ImageHeight, ‘window’, ‘bottom’, ‘right’, ‘black’, [], [])
  dev_set_window (WindowHandles[1])
  dev_disp_text (‘Press Run (F5) to continue’, ‘window’, ‘bottom’, ‘right’, ‘black’, [], [])
  stop ()
  endfor

---

模型训练阶段***************************************************
stop()
dev_update_off ()
*

• Training can be performed on a GPU or CPU.

• See the respective system requirements in the Installation Guide.

• If possible a GPU is used in this example.

• In case you explicitely wish to run this example on the CPU,

• choose the CPU device instead.
  query_available_dl_devices ([‘runtime’,‘runtime’], [‘gpu’,‘cpu’], DLDeviceHandles)
  if (|DLDeviceHandles| == 0)
  throw (‘No supported device found to continue this example.’)
  endif

• Due to the filter used in query_available_dl_devices, the first device is a GPU, if available.
  DLDevice := DLDeviceHandles[0]
  get_dl_device_param (DLDevice, ‘type’, DLDeviceType)
  if (DLDeviceType == ‘cpu’)

  • The number of used threads may have an impact
  • on the training duration.
    NumThreadsTraining := 4
    set_system (‘thread_num’, NumThreadsTraining)
    endif

---

• *** Set basic parameters. ***

---

• The following parameters need to be adapted frequently.
• Model parameters.
• Batch size.
  BatchSize := 2
• Initial learning rate.
  InitialLearningRate := 0.0005
• Momentum should be high if batch size is small.
  Momentum := 0.99
• Parameters used by train_dl_model.
• Number of epochs to train the model.
  NumEpochs := 60
• Evaluation interval (in epochs) to calculate evaluation measures on the validation split.
  EvaluationIntervalEpochs := 1
• Change the learning rate in the following epochs, e.g. [15, 30].
• Set it to [] if the learning rate should not be changed.
  ChangeLearningRateEpochs := 30
• Change the learning rate to the following values, e.g. InitialLearningRate * [0.1, 0.01].
• The tuple has to be of the same length as ChangeLearningRateEpochs.
  ChangeLearningRateValues := InitialLearningRate * 0.1

---

• *** Set advanced parameters. ***

---

• The following parameters might need to be changed in rare cases.

• Model parameter.

• Set the weight prior.
  WeightPrior := 0.00001

• Parameters used by train_dl_model.

• Control whether training progress is displayed (true/false).
  EnableDisplay := true

• Set a random seed for training.
  RandomSeed := 42
  set_system (‘seed_rand’, RandomSeed)

• In order to obtain nearly deterministic training results on the same GPU

• (system, driver, cuda-version) you could specify “cudnn_deterministic” as

• “true”. Note, that this could slow down training a bit.

• set_system (‘cudnn_deterministic’, ‘true’)

• Set generic parameters of create_dl_train_param.

• Please see the documentation of create_dl_train_param for an overview on all available parameters.
  GenParamName := []
  GenParamValue := []

• Augmentation parameter.

• If samples should be augmented during training, create the dict required by augment_dl_samples.

• Here, we set the augmentation percentage and method.
  create_dict (AugmentationParam)

• Percentage of samples to be augmented.
  set_dict_tuple (AugmentationParam, ‘augmentation_percentage’, 50)

• Mirror images along row and column.
  set_dict_tuple (AugmentationParam, ‘mirror’, ‘rc’)
  GenParamName := [GenParamName,‘augment’]
  GenParamValue := [GenParamValue,AugmentationParam]

• Change strategies.

• It is possible to change model parameters during training.

• Here, we change the learning rate if specified above.
  if (|ChangeLearningRateEpochs| > 0)
  create_dict (ChangeStrategy)

  • Specify the model parameter to be changed, here the learning rate.
    set_dict_tuple (ChangeStrategy, ‘model_param’, ‘learning_rate’)
  • Start the parameter value at ‘initial_value’.
    set_dict_tuple (ChangeStrategy, ‘initial_value’, InitialLearningRate)
  • Reduce the learning rate in the following epochs.
    set_dict_tuple (ChangeStrategy, ‘epochs’, ChangeLearningRateEpochs)
  • Reduce the learning rate to the following value at epoch 30.
    set_dict_tuple (ChangeStrategy, ‘values’, ChangeLearningRateValues)
  • Collect all change strategies as input.
    GenParamName := [GenParamName,‘change’]
    GenParamValue := [GenParamValue,ChangeStrategy]
    endif

• Serialization strategies.

• There are several options for saving intermediate models to disk (see create_dl_train_param).

• Here, the best and final model are saved to the paths set above.
  create_dict (SerializationStrategy)
  set_dict_tuple (SerializationStrategy, ‘type’, ‘best’)
  set_dict_tuple (SerializationStrategy, ‘basename’, BestModelBaseName)
  GenParamName := [GenParamName,‘serialize’]
  GenParamValue := [GenParamValue,SerializationStrategy]
  create_dict (SerializationStrategy)
  set_dict_tuple (SerializationStrategy, ‘type’, ‘final’)
  set_dict_tuple (SerializationStrategy, ‘basename’, FinalModelBaseName)
  GenParamName := [GenParamName,‘serialize’]
  GenParamValue := [GenParamValue,SerializationStrategy]

• Display parameters.

• In this example, the evaluation measure for the training spit is not displayed during

• training (default). If you want to do so, select a certain percentage of the training

• samples used to evaluate the model during training. A lower percentage helps to speed

• up the evaluation. If the evaluation measure for the training split shall

• not be displayed, set SelectedPercentageTrainSamples to 0.
  SelectedPercentageTrainSamples := 0

• Set the x-axis argument of the training plots.
  XAxisLabel := ‘epochs’
  create_dict (DisplayParam)
  set_dict_tuple (DisplayParam, ‘selected_percentage_train_samples’, SelectedPercentageTrainSamples)
  set_dict_tuple (DisplayParam, ‘x_axis_label’, XAxisLabel)
  GenParamName := [GenParamName,‘display’]
  GenParamValue := [GenParamValue,DisplayParam]

---

• *** Read initial model and dataset. ***

---

• Check if all necessary files exist.
  check_data_availability (ExampleDataDir, InitialModelFileName, DLDatasetFileName)
• Read in the model that was initialized during preprocessing.
  read_dl_model (InitialModelFileName, DLModelHandle)
• Read in the preprocessed DLDataset file.
  read_dict (DLDatasetFileName, [], [], DLDataset)

---

• *** Set model parameters. ***

---

• Set model hyper-parameters as specified in the settings above.
  set_dl_model_param (DLModelHandle, ‘learning_rate’, InitialLearningRate)
  set_dl_model_param (DLModelHandle, ‘momentum’, Momentum)
  if (BatchSize == ‘maximum’ and DLDeviceType == ‘gpu’)
  set_dl_model_param_max_gpu_batch_size (DLModelHandle, 100)
  else
  set_dl_model_param (DLModelHandle, ‘batch_size’, BatchSize)
  endif
  if (|WeightPrior| > 0)
  set_dl_model_param (DLModelHandle, ‘weight_prior’, WeightPrior)
  endif
• When the batch size is determined, set the device.
  set_dl_model_param (DLModelHandle, ‘device’, DLDevice)

---

• *** Train the model. ***

---

• Create training parameters.
  create_dl_train_param (DLModelHandle, NumEpochs, EvaluationIntervalEpochs, EnableDisplay, RandomSeed, GenParamName, GenParamValue, TrainParam)
• Start the training by calling the training operator
• train_dl_model_batch () within the following procedure.
  train_dl_model (DLDataset, DLModelHandle, TrainParam, 0.0, TrainResults, TrainInfos, EvaluationInfos)
• Stop after the training has finished, before closing the windows.
  dev_disp_text (‘Press Run (F5) to continue’, ‘window’, ‘bottom’, ‘right’, ‘black’, [], [])
  stop ()
• Close training windows.
  dev_close_window ()

---

模型评估阶段***********************************
dev_update_off ()
*

• In this example, the evaluation steps are explained in graphics windows,

• before they are executed. Set the following parameter to false in order to

• skip this visualization.
  ShowExampleScreens := true

• By default, this example uses a model pretrained by MVTec. To use the model

• which was trained in part 2 of this example series, set the following

• variable to false.
  UsePretrainedModel := true

• The evaluation can be performed on GPU or CPU.

• See the respective system requirements in the Installation Guide.

• If possible a GPU is used in this example.

• In case you explicitely wish to run this example on the CPU,

• choose the CPU device instead.
  query_available_dl_devices ([‘runtime’,‘runtime’], [‘gpu’,‘cpu’], DLDeviceHandles)
  if (|DLDeviceHandles| == 0)
  throw (‘No supported device found to continue this example.’)
  endif

• Due to the filter used in query_available_dl_devices, the first device is a GPU, if available.
  DLDevice := DLDeviceHandles[0]

---

• ** Set paths ***

---

• Example data folder containing the outputs of the previous example series.
  ExampleDataDir := ‘E:/2024-4-10’
• File name of the finetuned object detection model.
  RetrainedModelFileName := ExampleDataDir + ‘/best_dl_model_detection.hdl’
• Path to DL dataset.
• Note: Adapt DataDirectory after preprocessing with another image size.
  DataDirectory := ExampleDataDir + ‘/dldataset_pcb_512x320’
  DLDatasetFileName := DataDirectory + ‘/dl_dataset.hdict’

---

• ** Set evaluation parameters ***

---

• Specify measures of interest
  EvaluationMeasures := ‘all’
• Specify considered IoU thresholds.
  IoUThresholds := []
• Display detailed results for the following IoU threshold.
  DisplayIoUThreshold := 0.7
• Batch size used during evaluation.
  BatchSize := 1
• Specify evaluation subsets for objects of a certain size.
  AreaNames := []
  AreaMin := []
  AreaMax := []
• Specify the maximum number of detections considered for each measure.
  MaxNumDetections := []

---

• ** Read the model and data ***

---

• Check if all necessary files exist.
  check_data_availability_COPY_1 (ExampleDataDir, DLDatasetFileName, RetrainedModelFileName, UsePretrainedModel)
• Read the trained model.
  read_dl_model (RetrainedModelFileName, DLModelHandle)
• Set batch size of the model to 1 temporarily.
  set_dl_model_param (DLModelHandle, ‘batch_size’, 1)

set_dl_model_param (DLModelHandle, ‘device’, DLDevice)
*

• Read the evaluation data.
  read_dict (DLDatasetFileName, [], [], DLDataset)

---

• ** Set optimized parameters for inference ***

---

• To reduce the number of false positives, set lower values for
• ‘max_overlap’ (default = 0.5) and ‘max_overlap_class_agnostic’
• (default = 1.0) and a higher confidence threshold (default = 0.5).
  set_dl_model_param (DLModelHandle, ‘max_overlap_class_agnostic’, 0.7)
  set_dl_model_param (DLModelHandle, ‘max_overlap’, 0.2)
  set_dl_model_param (DLModelHandle, ‘min_confidence’, 0.6)

---

• ** First impression via visual inspection of results ***

---

• Create parameter dictionaries for visualization.
  create_dict (WindowHandleDict)
  create_dict (GenParam)
  set_dict_tuple (GenParam, ‘bbox_display_confidence’, false)
• Select test images randomly.
  get_dict_tuple (DLDataset, ‘samples’, DatasetSamples)
  find_dl_samples (DatasetSamples, ‘split’, ‘test’, ‘or’, DLSampleIndices)
  tuple_shuffle (DLSampleIndices, DLSampleIndicesShuffled)
• Apply the model and display results.
  for Index := 0 to 5 by 1
  read_dl_samples (DLDataset, DLSampleIndicesShuffled[Index], DLSampleBatch)
  apply_dl_model (DLModelHandle, DLSampleBatch, [], DLResultBatch)
  dev_display_dl_data (DLSampleBatch, DLResultBatch, DLDataset, ‘bbox_both’, GenParam, WindowHandleDict)
  dev_disp_text (‘Press Run (F5) to continue’, ‘window’, ‘bottom’, ‘right’, ‘black’, [], [])
  stop ()
  endfor

dev_close_window_dict (WindowHandleDict)
set_dl_model_param (DLModelHandle, ‘batch_size’, BatchSize)
*

---

• ** Evaluate object detection model on evaluation data ***

---

• Set generic evaluation parameters.
  create_dict (GenParamEval)
• Set the measures of interest.
  set_dict_tuple (GenParamEval, ‘measures’, EvaluationMeasures)
• Set maximum number of detections considered for each measure.
  if (|MaxNumDetections|)
  set_dict_tuple (GenParamEval, ‘max_num_detections’, MaxNumDetections)
  endif
• Set the evaluation area subsets.
  if (|AreaNames|)
  if ((|AreaNames| != |AreaMin|) or (|AreaNames| != |AreaMax|))
  throw (‘AreaNames, AreaMin, and AreaMax must have the same size.’)
  endif
  create_dict (AreaRanges)
  set_dict_tuple (AreaRanges, ‘name’, AreaNames)
  set_dict_tuple (AreaRanges, ‘min’, AreaMin)
  set_dict_tuple (AreaRanges, ‘max’, AreaMax)
  set_dict_tuple (GenParamEval, ‘area_ranges’, AreaRanges)
  endif
• Set IoU thresholds.
  if (|IoUThresholds|)
  set_dict_tuple (GenParamEval, ‘iou_threshold’, IoUThresholds)
  endif
• Enable detailed evaluation.
  set_dict_tuple (GenParamEval, ‘detailed_evaluation’, true)
• Show progress of evaluation.
  set_dict_tuple (GenParamEval, ‘show_progress’, true)
• Evaluate the finetuned model on the ‘test’ split of the dataset.
  evaluate_dl_model (DLDataset, DLModelHandle, ‘split’, ‘test’, GenParamEval, EvaluationResultDetection, EvalParams)
• Display results of the detailed evaluation.
  create_dict (DisplayParam)
• Set the IoU of interest. The default is the first ‘iou_threshold’ of EvalParams.
  if (|DisplayIoUThreshold| == 1)
  get_dict_tuple (EvalParams, ‘iou_threshold’, EvalIoUThresholds)
  if (find(EvalIoUThresholds,DisplayIoUThreshold) != -1)
  set_dict_tuple (DisplayParam, ‘iou_threshold’, DisplayIoUThreshold)
  else
  throw (‘No evaluation result for specified IoU threshold.’)
  endif
  endif
• Display detailed precision and recall
  set_dict_tuple (DisplayParam, ‘display_mode’, [‘pie_charts_precision’,‘pie_charts_recall’])
  create_dict (WindowHandleDict)
  dev_display_detection_detailed_evaluation (EvaluationResultDetection, EvalParams, DisplayParam, WindowHandleDict)
  dev_disp_text (‘Press Run (F5) to continue’, ‘window’, ‘top’, ‘right’, ‘black’, [], [])
  stop ()
  dev_close_window_dict (WindowHandleDict)
• Display confusion matrix.
  set_dict_tuple (DisplayParam, ‘display_mode’, ‘absolute_confusion_matrix’)
  dev_display_detection_detailed_evaluation (EvaluationResultDetection, EvalParams, DisplayParam, WindowHandleDict)
  dev_disp_text (‘Press Run (F5) to continue’, ‘window’, ‘bottom’, ‘right’, ‘black’, [], [])
  stop ()
  dev_close_window_dict (WindowHandleDict)
• Optimize the memory consumption.
  set_dl_model_param (DLModelHandle, ‘batch_size’, 1)
  set_dl_model_param (DLModelHandle, ‘optimize_for_inference’, ‘true’)
  write_dl_model (DLModelHandle, RetrainedModelFileName)
• Close the windows.
  dev_close_window_dict (WindowHandleDict)

---

模型测试阶段****************************************
dev_update_off ()
*

• In this example, the inference steps are explained in graphics windows,
• before they are executed. Set the following parameter to false in order to
• skip this visualization.
  ShowExampleScreens := true
• By default, this example uses a model pretrained by MVTec. To use the model
• which was trained in part 2 of this example series, set the following
• variable to false.
  UsePretrainedModel := true
• Inference can be done on a GPU or CPU.
• See the respective system requirements in the Installation Guide.
• If possible a GPU is used in this example.
• In case you explicitely wish to run this example on the CPU,
• choose the CPU device instead.
  query_available_dl_devices ([‘runtime’,‘runtime’], [‘gpu’,‘cpu’], DLDeviceHandles)
  if (|DLDeviceHandles| == 0)
  throw (‘No supported device found to continue this example.’)
  endif
• Due to the filter used in query_available_dl_devices, the first device is a GPU, if available.
  DLDevice := DLDeviceHandles[0]

---

• ** Set paths and parameters for inference ***

---

• We will demonstrate the inference on the example images.

• In a real application newly incoming images (not used for training or evaluation)

• would be used here.

• In this example, we read the images from file.

• Directory name with the images of the pill bag dataset.
  ExampleDir:=‘E:/2024-4-10’
  ImageDir := ExampleDir + ‘/PcbImgs’

• File name of the dict containing parameters used for preprocessing.

• Note: Adapt DataDirectory after preprocessing with another image size.
  DataDirectory := ExampleDir + ‘/dldataset_pcb_512x320’
  PreprocessParamFileName := DataDirectory + ‘/dl_preprocess_param.hdict’

• File name of the finetuned object detection model.
  RetrainedModelFileName := ExampleDir + ‘/best_dl_model_detection.hdl’

• Provide the class names and IDs.

• Class names.
  ClassNames := [‘SR’,‘MR’,‘BR’,‘C’,‘D’,‘U’]

• Respective class ids.
  ClassIDs := [0,1,2,3,4,5]

• Batch Size used during inference.
  BatchSizeInference := 1

• Postprocessing parameters for the detection model.
  MinConfidence := 0.6
  MaxOverlap := 0.2
  MaxOverlapClassAgnostic := 0.7

---

• ** Inference ***

---

• Check if all necessary files exist.
  check_data_availability_COPY_2 (ExampleDir, PreprocessParamFileName, RetrainedModelFileName, UsePretrainedModel)

• Read in the retrained model.
  read_dl_model (RetrainedModelFileName, DLModelHandle)

• Set the batch size.
  set_dl_model_param (DLModelHandle, ‘batch_size’, BatchSizeInference)

• Initialize the model for inference.
  set_dl_model_param (DLModelHandle, ‘device’, DLDevice)

• Set postprocessing parameters for model.
  set_dl_model_param (DLModelHandle, ‘min_confidence’, MinConfidence)
  set_dl_model_param (DLModelHandle, ‘max_overlap’, MaxOverlap)
  set_dl_model_param (DLModelHandle, ‘max_overlap_class_agnostic’, MaxOverlapClassAgnostic)

• Get the parameters used for preprocessing.
  read_dict (PreprocessParamFileName, [], [], DLPreprocessParam)

• Create window dictionary for displaying results.
  create_dict (WindowHandleDict)

• Create dictionary with dataset parameters necessary for displaying.
  create_dict (DLDataInfo)
  set_dict_tuple (DLDataInfo, ‘class_names’, ClassNames)
  set_dict_tuple (DLDataInfo, ‘class_ids’, ClassIDs)

• Set generic parameters for visualization.
  create_dict (GenParam)
  set_dict_tuple (GenParam, ‘scale_windows’, 1.2)

• Image Acquisition 01: Code generated by Image Acquisition 01
  list_files (‘E:/2024-4-10/PcbImgs’, [‘files’,‘follow_links’], ImageFiles)
  tuple_regexp_select (ImageFiles, [‘\.(tif|tiff|gif|bmp|jpg|jpeg|jp2|png|pcx|pgm|ppm|pbm|xwd|ima|hobj)$’,‘ignore_case’], ImageFiles)
  for Index := 0 to |ImageFiles| - 1 by 1
  read_image (ImageBatch, ImageFiles[Index])

  • Generate the DLSampleBatch.
    gen_dl_samples_from_images (ImageBatch, DLSampleBatch)
  • Preprocess the DLSampleBatch.
    preprocess_dl_samples (DLSampleBatch, DLPreprocessParam)
  • Apply the DL model on the DLSampleBatch.
    apply_dl_model (DLModelHandle, DLSampleBatch, [], DLResultBatch)
  • Postprocessing and visualization.
  • Loop over each sample in the batch.
    for SampleIndex := 0 to BatchSizeInference - 1 by 1
    *
    • Get sample and according results.
      DLSample := DLSampleBatch[SampleIndex]
      DLResult := DLResultBatch[SampleIndex]
    • Count detected pills for each class.
      get_dict_tuple (DLResult, ‘bbox_class_id’, DetectedClassIDs)
      tuple_gen_const (|ClassIDs|, 0, NumberDetectionsPerClass)
      for Index := 0 to |ClassIDs| - 1 by 1
      NumberDetectionsPerClass[Index] := sum(DetectedClassIDs [==] ClassIDs[Index])
      endfor
    • Create output text based on counted pills.
      create_counting_result_text (NumberDetectionsPerClass, ClassNames, Text, TextColor, TextBoxColor)
    • Display results and text.
      dev_display_dl_data (DLSample, DLResult, DLDataInfo, ‘bbox_result’, GenParam, WindowHandleDict)
      get_dict_tuple (WindowHandleDict, ‘bbox_result’, WindowHandles)
      dev_set_window (WindowHandles[0])
      set_display_font (WindowHandles[0], 16, ‘mono’, ‘true’, ‘false’)
      dev_disp_text (Text, ‘window’, ‘top’, ‘left’, TextColor, [‘box_color’,‘shadow’], [TextBoxColor,‘false’])
      dev_disp_text (‘Press Run (F5) to continue’, ‘window’, ‘bottom’, ‘right’, ‘black’, [], [])
      stop ()
      endfor
      endfor

• Close windows used for visualization.
  dev_close_window_dict (WindowHandleDict)