Halcon深度学习药片检测

1.应用示例思路

(1) 标注数据并获取halcon字典形式的训练数据；(2) 数据预处理；

(3) 模型训练；(4) 模型评估和验证；(5) 模型推理。

数据的标注使用labelimg工具，具体的参考以下博文：

https://blog.csdn.net/ctu_sue/article/details/127280183

 2.应用示例相关参数说明

(1) 创建目标检测模型(create_dl_model_detection)之前应设置的参数

(2) 目标检测模型训练时应设置的参数

(3) 目标检测模型评估和推理时应设置的参数

 3.应用示例相关代码

（1）解析xml，提取每张图像的目标类别和位置

import os
import xml.etree.ElementTree as ET

def Get_TrainData(xmlfile):

    TrainDataList = []
    Classes = []
    xml_file_name = os.path.basename(xmlfile)
    file_name = xml_file_name.split('.')[0]
    img_file_name = file_name + '.png'
    TrainDataList.append(img_file_name)

    with open(xmlfile,"r", encoding="utf-8") as in_file:
        tree = ET.parse(in_file)
        root = tree.getroot()

        for obj in root.iter('object'):
            cls = obj.find('name').text

            if cls not in Classes:
                Classes.append(cls)

            cls_id = Classes.index(cls)
            xmlbox = obj.find('bndbox')
            b = (int(xmlbox.find('xmin').text),int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text),int(xmlbox.find('ymax').text))

            list_file = "" + ",".join([str(a) for a in b]) + ',' + str(cls_id)
            TrainDataList.append(list_file)

    return  TrainDataList,Classes

SaveDir1='./pill data/DataLabel'
xml_file_path='./pill data/DataLabel'
xml_file_list = os.listdir(xml_file_path)
TotalTrainDataList=[]
TotalClasses=[]

for xmlfile in list(xml_file_list):

    xml_file_path = os.path.join(SaveDir1, xmlfile)

    TrainDataList, Classes = Get_TrainData(xml_file_path)

    TotalTrainDataList.append(TrainDataList)
    TotalClasses.append(Classes)

SaveDir2='./pill data/'
SaveDir3='./pill data/'

with open(os.path.join(SaveDir2,'TrainList.txt'), encoding="utf-8", mode="w") as f:

    for each_TrainDataList in TotalTrainDataList:
        f.write(" ".join(each_TrainDataList)+"n")

with open(os.path.join(SaveDir3,'classes.txt'), encoding="utf-8", mode="w") as f:
    for each_Classes in TotalClasses:
        f.write(",".join(each_Classes) + "n")

(2) 生成字典形式的训练数据

*1、变量定义

* 前边生成的类别文件
class_txt:='./InputFile/classes.txt'
* 前边生成的数据标注文件
train_txt:='./InputFile/TrainList.txt'
* 基于halcon转化脚本下的图像保存路径
ImageDir:='./DataImage'
* 基于halcon训练脚本下的图像保存路径
BaseImgDir:='./DataImage'
* 保存为halcon识别的训练文件
dict_File:='./InputFile/dl_dataset.hdict'

*2、读取种类

ClassID:=[]
ClassName:=[]

open_file (class_txt, 'input', FileHandle)
repeat
    fread_line(FileHandle, oneline, IsEOF)
    if(IsEOF == 1)
        break        
    endif
    if(oneline == ' ' or oneline=='n')
        continue
    endif
    tuple_regexp_replace (oneline, 'n', '', oneline)
    tuple_length (ClassID, Length)
    ClassID[Length]:=Length+1
    tuple_concat (ClassName, oneline, ClassName)
until (IsEOF)

*3、解析trainList.txt

TrainDataList:=[]
open_file (train_txt, 'input', FileHandle)
repeat
    fread_line(FileHandle, oneline, IsEOF)
    if(IsEOF == 1)
        break        
    endif
    if(oneline == ' ' or oneline=='n')
        continue
    endif
    tuple_regexp_replace (oneline, 'n', '', oneline)
    tuple_concat (TrainDataList, oneline, TrainDataList)
until (IsEOF)

*4、生成字典

class_ids:=[1,2,3,4,5,6,7,8,9,10]
class_names:=['黑圆','土圆','赭圆','白圆','鱼肝油','棕白胶囊','蓝白胶囊','白椭圆','黑椭圆','棕色胶囊']

AllSamples:=[]

for Index1 := 0 to |TrainDataList|-1 by 1
    EachTrainList:=TrainDataList[Index1]
    tuple_split (EachTrainList, ' ', DataList)
    imageFile:=DataList[0]
    tuple_length (DataList, Length)
    DataList:=DataList[1:Length-1]
    create_dict (SampleImage)
    set_dict_tuple (SampleImage, 'image_id', Index1+1)
    set_dict_tuple (SampleImage, 'image_file_name', imageFile)  
   
    bbox_label_id:=[]
    bbox_row1:=[]
    bbox_col1:=[]
    bbox_row2:=[]
    bbox_col2:=[]
    
    class_names_temp1:=[ClassName[Index1]]
    tuple_split (class_names_temp1, ',', class_names_temp2)
    
    for bbox_index:=0 to |DataList|-1 by 1
        bbox_data:=DataList[bbox_index]
        
        tuple_split (bbox_data, ',', bbox_data_list)
        
        tuple_number (bbox_data_list[4], Number)
        
        class_name:=class_names_temp2[Number]
        
        tuple_find_first (class_names, class_name, class_name_index)
        
        tuple_concat (bbox_label_id, class_name_index+1, bbox_label_id)
        
        tuple_number (bbox_data_list[1], Number)
        tuple_concat (bbox_row1, Number, bbox_row1)
        
        tuple_number (bbox_data_list[0], Number)
        tuple_concat (bbox_col1, Number, bbox_col1)
        
        tuple_number (bbox_data_list[3], Number)
        tuple_concat (bbox_row2, Number, bbox_row2)
        
        tuple_number (bbox_data_list[2], Number)
        tuple_concat (bbox_col2, Number, bbox_col2)
        
    endfor
    
    set_dict_tuple (SampleImage, 'bbox_label_id', bbox_label_id)
    set_dict_tuple (SampleImage, 'bbox_row1', bbox_row1)
    set_dict_tuple (SampleImage, 'bbox_col1', bbox_col1)
    set_dict_tuple (SampleImage, 'bbox_row2', bbox_row2)
    set_dict_tuple (SampleImage, 'bbox_col2', bbox_col2)
    
    tuple_concat (AllSamples, SampleImage, AllSamples)
    
endfor

*5、生成最终字典形式的训练数据

create_dict (DLDataset)
set_dict_tuple (DLDataset, 'image_dir', './DataImage')
set_dict_tuple (DLDataset, 'class_ids', class_ids)
set_dict_tuple (DLDataset, 'class_names', class_names)
set_dict_tuple (DLDataset, 'samples', AllSamples) 

write_dict (DLDataset, dict_File, [], [])

（3） 应用示例代码

dev_close_window ()
dev_update_off ()
set_system ('seed_rand', 42)

***0.)  设置输入输出路径(SET INPUT/OUTPUT PATHS)  ***

get_system ('example_dir', HalconExampleDir)
PillBagJsonFile := HalconExampleDir + '/hdevelop/Deep-Learning/Detection/pill_bag.json'
InputImageDir := HalconExampleDir + '/images/'
OutputDir := 'detect_pills_data'

*设置为true，如果运行此程序后应删除结果。
RemoveResults := false

***1.)准备(PREPARE )***

*我们从一个COCO文件中读取数据集。
*或者读取由MVTec深度学习工具使用read_dict()创建的DLDataset字典。

read_dl_dataset_from_coco (PillBagJsonFile, InputImageDir, dict{read_segmentation_masks: false}, DLDataset)

*创建适合数据集参数的检测模型。
DLModelDetectionParam := dict{image_dimensions: [512, 320, 3], max_level: 4}
DLModelDetectionParam.class_ids := DLDataset.class_ids
DLModelDetectionParam.class_names := DLDataset.class_names
create_dl_model_detection ('pretrained_dl_classifier_compact.hdl', |DLModelDetectionParam.class_ids|, DLModelDetectionParam, DLModelHandle)

*对DLDataset中的数据进行预处理。
split_dl_dataset (DLDataset, 60, 20, [])

*如有需要，现有的预处理数据将被覆盖。
PreprocessSettings := dict{overwrite_files: 'auto'}
create_dl_preprocess_param_from_model (DLModelHandle, 'none', 'full_domain', [], [], [], DLPreprocessParam)
preprocess_dl_dataset (DLDataset, OutputDir, DLPreprocessParam, PreprocessSettings, DLDatasetFileName)

*随机挑选10个预处理的样本进行可视化
WindowDict := dict{}
for Index := 0 to 9 by 1
    SampleIndex := round(rand(1) * (|DLDataset.samples| - 1))
    read_dl_samples (DLDataset, SampleIndex, DLSample)
    dev_display_dl_data (DLSample, [], DLDataset, 'bbox_ground_truth', [], WindowDict)
    dev_disp_text ('Press F5 to continue', 'window', 'bottom', 'right', 'black', [], [])
    stop ()
endfor
dev_close_window_dict (WindowDict)

***2.) 训练(TRAIN) ***
 
*训练可以在GPU或CPU上执行。
*本例中尽可能使用GPU。*如果你明确希望在CPU上运行这个例子，选择CPU设备。
query_available_dl_devices (['runtime', 'runtime'], ['gpu', 'cpu'], DLDeviceHandles)
if (|DLDeviceHandles| == 0)
    throw ('No supported device found to continue this example.')
endif

*由于query_available_dl_devices中使用了过滤，如果可用，第一个设备是GPU。
DLDevice := DLDeviceHandles[0]
get_dl_device_param (DLDevice, 'type', DLDeviceType)
if (DLDeviceType == 'cpu')
    *使用的线程数可能会对训练持续时间产生影响。
    NumThreadsTraining := 4
    set_system ('thread_num', NumThreadsTraining)
endif

*详细信息参见set_dl_model_param()和get_dl_model_param()的文档。
set_dl_model_param (DLModelHandle, 'batch_size', 1)
set_dl_model_param (DLModelHandle, 'learning_rate', 0.001)
set_dl_model_param (DLModelHandle, 'device', DLDevice)

*在这里，我们进行10次的短训练。为了更好的模型性能，增加epoch的数量，例如从10到60。

create_dl_train_param (DLModelHandle, 10, 1, 'true', 42, [], [], TrainParam)

*使用以下函数调用train_dl_model_batch()完成训练

train_dl_model (DLDataset, DLModelHandle, TrainParam, 0, TrainResults, TrainInfos, EvaluationInfos)

*读取由by train_dl_model保存的最佳模型文件。
read_dl_model ('model_best.hdl', DLModelHandle)
dev_disp_text ('Press F5 to continue', 'window', 'bottom', 'left', 'black', [], [])
stop ()

dev_close_window ()
dev_close_window ()

***3.) 评估(EVALUATE) ***
* 
GenParamEval := dict{detailed_evaluation: true, show_progress: true}

set_dl_model_param (DLModelHandle, 'device', DLDevice)
evaluate_dl_model (DLDataset, DLModelHandle, 'split', 'test', GenParamEval, EvaluationResult, EvalParams)

DisplayMode := dict{display_mode: ['pie_charts_precision', 'pie_charts_recall']}
dev_display_detection_detailed_evaluation (EvaluationResult, EvalParams, DisplayMode, WindowDict)
dev_disp_text ('Press F5 to continue', 'window', 'bottom', 'right', 'black', [], [])
stop ()
dev_close_window_dict (WindowDict)

*优化模型进行推理，也就是说，减少它的内存消耗。
set_dl_model_param (DLModelHandle, 'optimize_for_inference', 'true')
set_dl_model_param (DLModelHandle, 'batch_size', 1)
*保存此优化状态下的模型。
write_dl_model (DLModelHandle, 'model_best.hdl')

***4.) 推理(INFER) ***

*为了演示推理步骤，我们将训练好的模型应用于一些随机选择的示例图像。

list_image_files (InputImageDir + 'pill_bag', 'default', 'recursive', ImageFiles)
tuple_shuffle (ImageFiles, ImageFilesShuffled)

*创建用于可视化的窗口字典。
WindowDict := dict{}
DLDatasetInfo := dict{}
get_dl_model_param (DLModelHandle, 'class_ids', DLDatasetInfo.class_ids)
get_dl_model_param (DLModelHandle, 'class_names', DLDatasetInfo.class_names)
for IndexInference := 0 to 9 by 1
    read_image (Image, ImageFilesShuffled[IndexInference])
    gen_dl_samples_from_images (Image, DLSampleInference)
    preprocess_dl_samples (DLSampleInference, DLPreprocessParam)
    apply_dl_model (DLModelHandle, DLSampleInference, [], DLResult)
    dev_display_dl_data (DLSampleInference, DLResult, DLDataset, 'bbox_result', [], WindowDict)
    dev_disp_text ('Press F5 to continue', 'window', 'bottom', 'right', 'black', [], [])
    stop ()
endfor
dev_close_window_dict (WindowDict)

***5.) 删除文件(REMOVE FILES) ***

clean_up_output (OutputDir, RemoveResults)

如果不想自己标注数据的，可以下载我整理好的资源：https://download.csdn.net/download/qq_44744164/88595779

代码007普通

打赏 收藏 海报 链接