精简代码

CMakeLists.txt

@@ -2,7 +2,7 @@
 cmake_minimum_required(VERSION 3.5)
 
 # 设置项目名
-project(MIGraphX_Samples)
+project(YOLOV5)
 
 # 设置编译器
 set(CMAKE_CXX_COMPILER g++)
@@ -12,7 +12,6 @@ set(CMAKE_BUILD_TYPE release)
 # 添加头文件路径
 set(INCLUDE_PATH    ${CMAKE_CURRENT_SOURCE_DIR}/Src/
                     ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/ 
-                    ${CMAKE_CURRENT_SOURCE_DIR}/Src/Detector/
                     $ENV{DTKROOT}/include/
                     ${CMAKE_CURRENT_SOURCE_DIR}/depend/include/)
 include_directories(${INCLUDE_PATH})
@@ -37,10 +36,9 @@ link_libraries(${LIBRARY})
 
 # 添加源文件
 set(SOURCE_FILES ${CMAKE_CURRENT_SOURCE_DIR}/Src/main.cpp
-                ${CMAKE_CURRENT_SOURCE_DIR}/Src/Sample.cpp
-                ${CMAKE_CURRENT_SOURCE_DIR}/Src/Detector/DetectorYOLOV5.cpp
+                ${CMAKE_CURRENT_SOURCE_DIR}/Src/YOLOV5.cpp
                 ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/CommonUtility.cpp
                 ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/Filesystem.cpp)
 
 # 添加可执行目标
-add_executable(MIGraphX_Samples ${SOURCE_FILES})
+add_executable(YOLOV5 ${SOURCE_FILES})

Doc/Tutorial_Cpp.md

+# YOLOV5检测器
+
+YOLOV5模型是目前工业界使用较多的算法，官方提供了多个不同版本的预训练模型，本份文档主要介绍了如何将MIGraphX推理结果进行模型初始化、预处理以及后处理，该示例推理流程对YOLOV5其他版本的模型同样适用。
+
+## 模型简介
+
+YOLOV5是一种单阶段目标检测算法，该算法在YOLOV4的基础上添加了一些新的改进思路，使其速度与精度都得到了极大的性能提升。具体包括：输入端的Mosaic数据增强、自适应锚框计算、自适应图片缩放操作；主干网络的Focus结构与CSP结构；Neck端的FPN+PAN结构；输出端的损失函数GIOU_Loss以及预测框筛选的DIOU_nms。网络结构如图所示。
+
+<img src=./YOLOV5_01.jpg style="zoom:100%;" align=middle>
+
+## 检测器参数设置
+
+samples工程中的Resource/Configuration.xml文件的DetectorYOLOV5节点表示YOLOV5检测器的参数，相关参数主要依据官方推理示例进行设置。各个参数含义如下：
+
+- ModelPath：yolov5模型存放路径
+- ClassNameFile：coco数据集类别文件存放路径
+- UseFP16：是否使用FP16推理模式
+- NumberOfClasses：检测类别数量
+- ConfidenceThreshold：置信度阈值，用于判断anchor内的物体是否为正样本
+- NMSThreshold：非极大值抑制阈值，用于消除重复框
+- ObjectThreshold：用于判断anchor内部是否有物体
+
+```
+<ModelPath>"../Resource/Models/YOLOV5s.onnx"</ModelPath>
+<ClassNameFile>"../Resource/Models/coco.names"</ClassNameFile>
+<UseFP16>0</UseFP16><!--是否使用FP16-->
+<NumberOfClasses>80</NumberOfClasses><!--类别数(不包括背景类)，COCO:80,VOC:20-->
+<ConfidenceThreshold>0.25</ConfidenceThreshold>
+<NMSThreshold>0.5</NMSThreshold>
+<ObjectThreshold>0.5</ObjectThreshold>
+```
+
+## 模型初始化
+
+模型初始化首先通过parse_onnx()函数加载YOLOV5的onnx模型，并可以通过program的get_parameter_shapes()函数获取网络的输入属性。完成模型加载之后需要使用compile()方法编译模型，编译模式使用migraphx::gpu::target{}设为GPU模式，编译过程主要基于MIGraphX IR完成各种优化。同时如果需要使用低精度量化进行推理，可以使用quantize_fp16()函数实现。
+
+```
+ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializationParameterOfDetector)
+{
+    ...
+    
+    //模型加载
+    net = migraphx::parse_onnx(modelPath);
+    LOG_INFO(stdout,"succeed to load model: %s\n",GetFileName(modelPath).c_str());
+
+    // 获取模型输入属性
+    std::pair<std::string, migraphx::shape> inputAttribute=*(net.get_parameter_shapes().begin());
+    inputName=inputAttribute.first;
+    inputShape=inputAttribute.second;
+    int N=inputShape.lens()[0];
+    int C=inputShape.lens()[1];
+    int H=inputShape.lens()[2];
+    int W=inputShape.lens()[3];
+    inputSize=cv::Size(W,H);
+
+    // 设置模型为GPU模式
+    migraphx::target gpuTarget = migraphx::gpu::target{};
+
+    // 量化    
+    if(useFP16)
+    {
+        migraphx::quantize_fp16(net);
+    }
+
+    // 编译模型
+    migraphx::compile_options options;
+    options.device_id=0; // 设置GPU设备，默认为0号设备
+    options.offload_copy=true; // 设置offload_copy
+    net.compile(gpuTarget,options);
+    LOG_INFO(stdout,"succeed to compile model: %s\n",GetFileName(modelPath).c_str());
+
+    ...
+}
+```
+
+## 预处理
+
+在将数据输入到模型之前，需要对图像做如下预处理操作：
+
+1. 转换数据排布为NCHW
+2. 归一化[0.0, 1.0]
+3. 将输入数据的尺寸变换到YOLOV5输入大小（1，3，608，608）
+
+```
+ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDetection> &resultsOfDetection)
+{ 
+  ...
+  
+    // 预处理并转换为NCHW
+    cv::Mat inputBlob;
+    blobFromImage(srcImage,   // 输入数据
+                    inputBlob,  // 输出数据
+                    1 / 255.0,  //归一化
+                    inputSize,  //YOLOV5输入尺寸，本示例为608x608
+                    Scalar(0, 0, 0),  //未减去均值
+                    true,  //转换RB通道
+                    false);
+                    
+   ...
+}
+```
+
+## 推理
+
+完成图像预处理以及YOLOV5目标检测相关参数设置之后开始执行推理，利用migraphx推理计算得到YOLOV5模型的输出。
+
+```
+ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDetection> &resultsOfDetection)
+{
+
+	...
+    // 创建输入数据
+    std::unordered_map<std::string, migraphx::shape> inputData;
+    inputData[inputName]= migraphx::argument{inputShape, (float*)inputBlob.data};
+
+    // 推理
+    std::vector<migraphx::argument> inferenceResults = net.eval(inputData);
+
+    // 获取推理结果
+    std::vector<cv::Mat> outs;
+    migraphx::argument result = inferenceResults[0]; 
+
+    // 转换为cv::Mat
+    migraphx::shape outputShape = result.get_shape();
+    int shape[]={outputShape.lens()[0],outputShape.lens()[1],outputShape.lens()[2]};
+    cv::Mat out(3,shape,CV_32F);
+    memcpy(out.data,result.data(),sizeof(float)*outputShape.elements());
+    outs.push_back(out);
+    
+    ...
+}
+```
+
+YOLOV5的MIGraphX推理结果inferenceResults是一个std::vector< migraphx::argument >类型，YOLOV5的onnx模型包含一个输出，所以result等于inferenceResults[0]，result包含三个维度：outputShape.lens()[0]=1表示batch信息，outputShape.lens()[1]=22743表示生成anchor数量，outputShape.lens()[2]=85表示对每个anchor的预测信息。同时可将85拆分为4+1+80，前4个参数用于判断每一个特征点的回归参数，回归参数调整后可以获得预测框，第5个参数用于判断每一个特征点是否包含物体，最后80个参数用于判断每一个特征点所包含的物体种类。获取上述信息之后进行anchors筛选，筛选过程分为两个步骤：
+
+- 第一步根据objectThreshold阈值进行筛选，大于该阈值则判断当前anchor内包含物体，小于该阈值则判断无物体
+- 第二步根据confidenceThreshold阈值进行筛选，当满足第一步阈值anchor的最大置信度得分maxClassScore大于该阈值，则进一步获取当前anchor的坐标信息和预测物体类别信息，小于该阈值则不做处理。
+
+```
+ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDetection> &resultsOfDetection)
+{
+
+	...
+    //获取先验框的个数numProposal=22743
+    numProposal = outs[0].size[1];
+    //每个anchor的预测信息数量numOut=85
+    numOut = outs[0].size[2];
+    outs[0] = outs[0].reshape(0, numProposal);
+
+    std::vector<float> confidences;
+    std::vector<cv::Rect> boxes;
+    std::vector<int> classIds;
+    //原图尺寸与模型输入尺寸的缩放比例
+    float ratioh = (float)srcImage.rows / inputSize.height, ratiow = (float)srcImage.cols / inputSize.width;
+
+    //计算cx,cy,w,h,box_sore,class_sore
+    int n = 0, rowInd = 0;
+    float* pdata = (float*)outs[0].data;
+    for (n = 0; n < numProposal; n++)
+    {
+        //获取当前anchor是否包含物体的概率值
+        float boxScores = pdata[4];
+        
+        //第一次筛选，判断anchor内是否包含物体
+        if (boxScores > yolov5Parameter.objectThreshold)
+        {
+            //获取每个anchor内部预测的80个类别概率信息
+            cv::Mat scores = outs[0].row(rowInd).colRange(5, numOut);
+            cv::Point classIdPoint;
+            double maxClassScore;
+            
+            //获取80个类别中最大概率值和对应的类别ID
+            cv::minMaxLoc(scores, 0, &maxClassScore, 0, &classIdPoint);
+            maxClassScore *= boxScores;
+            
+            //第二次筛选，判断当前anchor的最大置信度得分是否满足阈值
+            if (maxClassScore > yolov5Parameter.confidenceThreshold)
+            {
+                const int classIdx = classIdPoint.x;
+                
+                //将每个anchor坐标按缩放比例映射到原图
+                float cx = pdata[0] * ratiow;
+                float cy = pdata[1] * ratioh;
+                float w = pdata[2] * ratiow;
+                float h = pdata[3] * ratioh;
+                //获取anchor的左上角坐标
+                int left = int(cx - 0.5 * w);
+                int top = int(cy - 0.5 * h);
+
+                confidences.push_back((float)maxClassScore);
+                boxes.push_back(cv::Rect(left, top, (int)(w), (int)(h)));
+                classIds.push_back(classIdx);
+            }
+        }
+        rowInd++;
+        pdata += numOut;
+    }
+	
+	...
+}
+```
+
+为了消除重叠锚框，输出最终的YOLOV5目标检测结果，执行非极大值抑制对筛选之后的anchor进行处理，最后保存检测结果到resultsOfDetection中。
+
+```
+ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDetection> &resultsOfDetection)
+{
+
+	...
+    
+    // 执行non maximum suppression消除冗余重叠boxes
+    std::vector<int> indices;
+    cv::dnn::NMSBoxes(boxes, confidences, yolov5Parameter.confidenceThreshold, yolov5Parameter.nmsThreshold, indices);
+    for (size_t i = 0; i < indices.size(); ++i)
+    {
+        int idx = indices[i];
+        int classID=classIds[idx];
+        string className=classNames[classID];
+        float confidence=confidences[idx];
+        cv::Rect box = boxes[idx];
+		
+        //保存每个最终预测anchor的坐标值、置信度分数、类别ID
+        ResultOfDetection result;
+        result.boundingBox=box;
+        result.confidence=confidence;// confidence
+        result.classID=classID; // label
+        result.className=className;
+        resultsOfDetection.push_back(result);
+    }
+
+    ...
+}
+```

Doc/Tutorial_Python.md

+# YOLOV5检测器
+
+本份文档主要介绍如何基于MIGraphX构建YOLOV5的Python推理示例，根据文档描述可以了解怎样运行该Python示例得到YOLOV5的目标检测结果。
+
+## 模型简介
+
+YOLOV5是一种单阶段目标检测算法，该算法在YOLOV4的基础上添加了一些新的改进思路，使其速度与精度都得到了极大的性能提升。具体包括：输入端的Mosaic数据增强、自适应锚框计算、自适应图像缩放操作；主干网络的Focus结构与CSP结构；Neck端的FPN+PAN结构；输出端的损失函数GIOU_Loss以及预测框筛选的DIOU_nms。网络结构如图所示。
+
+<img src=./YOLOV5_01.jpg style="zoom:100%;" align=middle>
+
+## 预处理
+
+待检测图像输入模型进行检测之前需要进行预处理，主要包括调整输入的尺寸，归一化等操作。
+
+1. 转换数据排布为NCHW
+2. 归一化[0.0, 1.0]
+3. 调整输入数据的尺寸为（1，3，608，608）
+
+```
+def prepare_input(self, image):
+    self.img_height, self.img_width = image.shape[:2]
+    input_img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    # 调整图像的尺寸
+    input_img = cv2.resize(input_img, (self.inputWidth, self.inputHeight))
+    # 维度转换HWC->CHW
+    input_img = input_img.transpose(2, 0, 1)
+    # 维度拓展，增加batch维度
+    input_img = np.expand_dims(input_img, 0)
+    input_img = np.ascontiguousarray(input_img)
+    input_img = input_img.astype(np.float32)
+    # 归一化
+    input_img = input_img / 255
+
+    return input_img
+```
+
+其中模型输入的inputWidth、inputHeight通过migraphx对输入模型进行解析获取，代码位置见YOLOV5类初始化位置。
+
+```
+class YOLOv5:
+    def __init__(self, path, obj_thres=0.5, conf_thres=0.25, iou_thres=0.5):
+        self.objectThreshold = obj_thres
+        self.confThreshold = conf_thres
+        self.nmsThreshold = iou_thres
+
+        # 获取模型检测的类别信息
+        self.classNames = list(map(lambda x: x.strip(), open('../Resource/Models/coco.names', 'r').readlines()))
+
+        # 解析推理模型
+        self.model = migraphx.parse_onnx(path)
+
+        # 获取模型的输入name
+        self.inputName = self.model.get_parameter_names()[0]
+
+        # 获取模型的输入尺寸
+        inputShape = self.model.get_parameter_shapes()[self.inputName].lens()
+        self.inputHeight = int(inputShape[2])
+        self.inputWidth = int(inputShape[3])
+```
+
+## 推理
+
+输入图像预处理完成之后开始进行推理，首先需要利用migraphx进行编译，然后对输入数据进行前向计算得到模型的输出result，在detect函数中调用定义的process_output函数对result进行后处理，得到图像中含有物体的anchor坐标信息、类别置信度、类别ID。
+
+```
+def detect(self, image):
+    # 输入图像预处理
+    input_img = self.prepare_input(image)
+
+    # 模型编译
+    self.model.compile(t=migraphx.get_target("gpu"), device_id=0)  # device_id: 设置GPU设备，默认为0号设备
+    print("Success to compile")
+    # 执行推理
+    print("Start to inference")
+    start = time.time()
+    result = self.model.run({self.model.get_parameter_names()[0]: input_img})
+    print('net forward time: {:.4f}'.format(time.time() - start))
+    # 模型输出结果后处理
+    boxes, scores, class_ids = self.process_output(result)
+
+    return boxes, scores, class_ids
+```
+
+其中对migraphx推理输出result进行后处理，首先需要对生成的anchor根据是否有物体阈值objectThreshold、置信度阈值confThreshold进行筛选，相关过程定义在process_output函数中。获取筛选后的anchor的坐标信息之后，需要将坐标映射到原图中的位置，相关过程定义在rescale_boxes函数中。
+
+```
+def process_output(self, output):
+    predictions = np.squeeze(output[0])
+
+    # 筛选包含物体的anchor
+    obj_conf = predictions[:, 4]
+    predictions = predictions[obj_conf > self.objectThreshold]
+    obj_conf = obj_conf[obj_conf > self.objectThreshold]
+
+    # 筛选大于置信度阈值的anchor
+    predictions[:, 5:] *= obj_conf[:, np.newaxis]
+    scores = np.max(predictions[:, 5:], axis=1)
+    valid_scores = scores > self.confThreshold
+    predictions = predictions[valid_scores]
+    scores = scores[valid_scores]
+
+    # 获取最高置信度分数对应的类别ID
+    class_ids = np.argmax(predictions[:, 5:], axis=1)
+
+    # 获取每个物体对应的anchor
+    boxes = self.extract_boxes(predictions)
+
+    # 执行非极大值抑制消除冗余anchor
+    indices = cv2.dnn.NMSBoxes(boxes.tolist(), scores.tolist(), self.confThreshold, self.nmsThreshold).flatten()
+
+    return boxes[indices], scores[indices], class_ids[indices]
+
+def rescale_boxes(self, boxes):
+    # 对anchor尺寸进行变换
+    input_shape = np.array([self.inputWidth, self.inputHeight, self.inputWidth, self.inputHeight])
+    boxes = np.divide(boxes, input_shape, dtype=np.float32)
+    boxes *= np.array([self.img_width, self.img_height, self.img_width, self.img_height])
+    return boxes
+```
+
+根据获取的detect函数输出的boxes、scores、class_ids信息在原图进行结果可视化，包括绘制图像中检测到的物体位置、类别和置信度分数，得到最终的YOLOV5目标检测结果输出。
+
+```
+def draw_detections(self, image, boxes, scores, class_ids):
+    for box, score, class_id in zip(boxes, scores, class_ids):
+        cx, cy, w, h = box.astype(int)
+
+        # 绘制检测物体框
+        cv2.rectangle(image, (cx, cy), (cx + w, cy + h), (0, 255, 255), thickness=2)
+        label = self.classNames[class_id]
+        label = f'{label} {int(score * 100)}%'
+        labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
+        cv2.putText(image, label, (cx, cy - 10), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), thickness=2)
+    return image
+```

Python/YoloV5_infer_migraphx.py

@@ -14,7 +14,7 @@ class YOLOv5:
         self.nmsThreshold = iou_thres
 
         # 获取模型检测的类别信息
-        self.classNames = list(map(lambda x: x.strip(), open('../Resource/Models/Detector/YOLOV5/coco.names', 'r').readlines()))
+        self.classNames = list(map(lambda x: x.strip(), open('../Resource/Models/coco.names', 'r').readlines()))
 
         # 解析推理模型
         self.model = migraphx.parse_onnx(path)
@@ -119,7 +119,7 @@ class YOLOv5:
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument('--imgpath', type=str, default='../Resource/Images/bus.jpg', help="image path")
-    parser.add_argument('--modelpath', type=str, default='../Resource/Models/Detector/YOLOV5/yolov5s.onnx', help="onnx filepath")
+    parser.add_argument('--modelpath', type=str, default='../Resource/Models/yolov5s.onnx', help="onnx filepath")
     parser.add_argument('--objectThreshold', default=0.5, type=float, help='class confidence')
     parser.add_argument('--confThreshold', default=0.25, type=float, help='class confidence')
     parser.add_argument('--nmsThreshold', default=0.5, type=float, help='nms iou thresh')

README.md

@@ -13,7 +13,11 @@ YoloV5模型的主要改进思路有以下几点：
 - Neck端的FPN+PAN结构；
 - 输出端的损失函数GIOU_Loss以及预测框筛选的DIOU_nms。
 
-## 构建安装
+## python版本推理
+
+下面介绍如何运行python代码示例，具体推理代码解析，在Doc/Tutorial_Python.md中有详细说明。
+
+### 构建安装
 
 在光源可拉取推理的docker镜像，YoloV5工程推荐的镜像如下：
 
@@ -21,6 +25,36 @@ YoloV5模型的主要改进思路有以下几点：
 docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
 ```
 
+### 推理示例
+
+YoloV5模型的推理示例程序是YoloV5_infer_migraphx.py，使用如下命令运行该推理示例：
+
+```
+# 进入python示例目录
+cd ./Python
+
+# 安装依赖
+pip install -r requirements.txt
+
+# 运行程序
+python YoloV5_infer_migraphx.py \
+	--imgpath 测试图像路径 \ 
+	--modelpath onnx模型路径 \
+	--objectThreshold 判断是否有物体阈值，默认0.5 \
+	--confThreshold 置信度阈值，默认0.25 \
+	--nmsThreshold nms阈值，默认0.5 \
+```
+
+程序运行结束会在当前目录生成YoloV5检测结果图像。
+
+<img src="./Resource/Images/Result.jpg" alt="Result_2" style="zoom: 50%;" />
+
+## C++版本推理
+
+下面介绍如何运行C++代码示例，具体推理代码解析，在Doc/Tutorial_Cpp.md目录中有详细说明。
+
+参考Python版本推理中的构建安装，在光源中拉取推理的docker镜像。
+
 ### 安装Opencv依赖
 
 ```python
@@ -64,43 +98,24 @@ export LD_LIBRARY_PATH=<path_to_migraphx_samples>/depend/lib/:$LD_LIBRARY_PATH
 source ~/.bashrc
 ```
 
-## 推理
-
-### C++版本推理
+### 推理示例
 
-成功编译YoloV5工程后，在build目录下输入如下命令运行该示例：
+成功编译YoloV5工程后，执行如下命令运行该示例：
 
 ```
-./MIGraphX_Samples 0
-```
-
-程序运行结束会在build目录生成YoloV5检测结果图像。
-
-<img src="./Resource/Images/Result.jpg" alt="Result" style="zoom:50%;" />
+# 进入migraphx samples工程根目录
+cd <path_to_migraphx_samples> 
 
-### python版本推理
-
-YoloV5模型的推理示例程序是YoloV5_infer_migraphx.py，使用如下命令运行该推理示例：
+# 进入build目录
+cd ./build/
 
+# 执行示例程序
+./YOLOV5
 ```
-# 进入python示例目录
-cd ./Python
-
-# 安装依赖
-pip install -r requirements.txt
 
-# 运行程序
-python YoloV5_infer_migraphx.py \
-	--imgpath 测试图像路径 \ 
-	--modelpath onnx模型路径 \
-	--objectThreshold 判断是否有物体阈值，默认0.5 \
-	--confThreshold 置信度阈值，默认0.25 \
-	--nmsThreshold nms阈值，默认0.5 \
-```
-
-程序运行结束会在当前目录生成YoloV5检测结果图像。
+程序运行结束会在build目录生成YoloV5检测结果图像。
 
-<img src="./Resource/Images/Result.jpg" alt="Result_2" style="zoom: 50%;" />
+<img src="./Resource/Images/Result.jpg" alt="Result" style="zoom:50%;" />
 
 ## 历史版本
 

Resource/Configuration.xml

@@ -3,8 +3,8 @@
 
 	<!--YOLOV5检测器 -->
 	<DetectorYOLOV5>
-		<ModelPath>"../Resource/Models/Detector/YOLOV5/yolov5s.onnx"</ModelPath>
-		<ClassNameFile>"../Resource/Models/Detector/YOLOV5/coco.names"</ClassNameFile>
+		<ModelPath>"../Resource/Models/yolov5s.onnx"</ModelPath>
+		<ClassNameFile>"../Resource/Models/coco.names"</ClassNameFile>
 		<UseFP16>0</UseFP16><!--是否使用FP16-->
 		<NumberOfClasses>80</NumberOfClasses><!--类别数(不包括背景类)，COCO:80,VOC:20-->
 		<ConfidenceThreshold>0.25</ConfidenceThreshold>

Src/Sample.cpp

-#include <Sample.h>
-#include <opencv2/dnn.hpp>
-#include <SimpleLog.h>
-#include <Filesystem.h>
-#include <DetectorYOLOV5.h>
-#include <fstream>
-
-using namespace std;
-using namespace cv;
-using namespace cv::dnn;
-using namespace migraphx;
-using namespace migraphxSamples;
-
-void Sample_DetectorYOLOV5()
-{
-    // 创建YOLOV5检测器
-    DetectorYOLOV5 detector;
-    InitializationParameterOfDetector initParamOfDetectorYOLOV5;
-    initParamOfDetectorYOLOV5.parentPath = "";
-    initParamOfDetectorYOLOV5.configFilePath = CONFIG_FILE;
-    initParamOfDetectorYOLOV5.logName = "";
-    ErrorCode errorCode=detector.Initialize(initParamOfDetectorYOLOV5);
-    if(errorCode!=SUCCESS)
-    {
-        LOG_ERROR(stdout, "fail to initialize detector!\n");
-        exit(-1);
-    }
-    LOG_INFO(stdout, "succeed to initialize detector\n");
-
-    // 读取测试图片
-    Mat srcImage=imread("../Resource/Images/bus.jpg",1);
-
-    // 推理
-    std::vector<ResultOfDetection> predictions;
-    double time1 = getTickCount();
-    detector.Detect(srcImage,predictions);
-    double time2 = getTickCount();
-    double elapsedTime = (time2 - time1)*1000 / getTickFrequency();
-    LOG_INFO(stdout, "inference time:%f ms\n", elapsedTime);
-
-    // 获取推理结果
-    LOG_INFO(stdout,"========== Detection Results ==========\n");
-    for(int i=0;i<predictions.size();++i)
-    {
-        ResultOfDetection result=predictions[i];
-        cv::rectangle(srcImage,result.boundingBox,Scalar(0,255,255),2);
-
-        string label = format("%.2f", result.confidence);
-        label = result.className + " " + label;
-        int left = predictions[i].boundingBox.x;
-        int top = predictions[i].boundingBox.y;
-        int baseLine;
-	    Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
-	    top = max(top, labelSize.height);
-        putText(srcImage, label, Point(left, top-10), FONT_HERSHEY_SIMPLEX, 1, Scalar(0, 255, 255), 2);
-
-        LOG_INFO(stdout,"box:%d %d %d %d,label:%d,confidence:%f\n",predictions[i].boundingBox.x,
-        predictions[i].boundingBox.y,predictions[i].boundingBox.width,predictions[i].boundingBox.height,predictions[i].classID,predictions[i].confidence);
-    }
-    imwrite("Result.jpg",srcImage);
-    LOG_INFO(stdout,"Detection results have been saved to ./Result.jpg\n");
-}
-

Src/Sample.h

-// 示例程序
-
-#ifndef __SAMPLE_H__
-#define __SAMPLE_H__
-
-// YOLOV5 sample
-void Sample_DetectorYOLOV5();
-
-#endif
\ No newline at end of file

Src/Utility/CommonDefinition.h

-// 常用数据类型和宏定义
+// 常用定义
 
 #ifndef __COMMON_DEFINITION_H__
 #define __COMMON_DEFINITION_H__
 
-#include <string>
 #include <opencv2/opencv.hpp>
 
-using namespace std;
-using namespace cv;
-
 namespace migraphxSamples
 {
    
@@ -21,20 +17,7 @@ namespace migraphxSamples
 
 #define CONFIG_FILE                                                     "../Resource/Configuration.xml"
 
-typedef struct  __Time
-{
-    string year;
-    string month;
-    string day;
-    string hour;
-    string minute;
-    string second;
-    string millisecond; // ms
-    string microsecond; // us
-    string weekDay;
-}_Time;
-
-typedef enum  _ErrorCode
+typedef enum _ErrorCode
 {
     SUCCESS=0,  // 0
     MODEL_NOT_EXIST, // 模型不存在
@@ -44,7 +27,7 @@ typedef enum  _ErrorCode
     IMAGE_ERROR, // 图像错误
 }ErrorCode;
 
-typedef struct  _ResultOfPrediction
+typedef struct _ResultOfPrediction
 {
     float confidence;
     int label;
@@ -52,27 +35,24 @@ typedef struct  _ResultOfPrediction
 
 }ResultOfPrediction;
 
-typedef struct  _ResultOfDetection
+typedef struct _ResultOfDetection
 {
-    Rect boundingBox;
+    cv::Rect boundingBox;
     float confidence;
     int classID;
-    string className;
+    std::string className;
     bool exist;
 
     _ResultOfDetection():confidence(0.0f),classID(0),exist(true){}
 
 }ResultOfDetection;
 
-typedef struct  _InitializationParameterOfDetector
+typedef struct _InitializationParameterOfDetector
 {
     std::string parentPath;
     std::string configFilePath;
-    cv::Size inputSize;
-    std::string logName;
 }InitializationParameterOfDetector;
 
-
 }
 
 #endif

Src/Utility/CommonUtility.cpp

 #include <CommonUtility.h>
-#include <assert.h>
-#include <ctype.h>
-#include <time.h>
-#include <stdlib.h>
-#include <algorithm>
-#include <sstream>
-#include <vector>
-
-#ifdef _WIN32
-#include <io.h>
-#include <direct.h>
-#include <Windows.h>
-#else
-#include <unistd.h>
-#include <dirent.h>
-#include <sys/stat.h>
-#include <sys/time.h>
-#endif
-
-#include <SimpleLog.h>
 
 namespace migraphxSamples
 {
 
-
-_Time GetCurrentTime3()
-{
-    _Time currentTime;
-
-#if (defined WIN32 || defined _WIN32)
-	SYSTEMTIME systemTime;
-	GetLocalTime(&systemTime);
-
-	char temp[8] = { 0 };
-	sprintf(temp, "%04d", systemTime.wYear);
-	currentTime.year=string(temp);
-	sprintf(temp, "%02d", systemTime.wMonth);
-	currentTime.month=string(temp);
-	sprintf(temp, "%02d", systemTime.wDay);
-	currentTime.day=string(temp);
-	sprintf(temp, "%02d", systemTime.wHour);
-	currentTime.hour=string(temp);
-	sprintf(temp, "%02d", systemTime.wMinute);
-	currentTime.minute=string(temp);
-	sprintf(temp, "%02d", systemTime.wSecond);
-	currentTime.second=string(temp);
-	sprintf(temp, "%03d", systemTime.wMilliseconds);
-	currentTime.millisecond=string(temp);
-	sprintf(temp, "%d", systemTime.wDayOfWeek);
-	currentTime.weekDay=string(temp);
-#else
-	struct timeval    tv;
-	struct tm         *p;
-	gettimeofday(&tv, NULL);
-	p = localtime(&tv.tv_sec);
-
-	char temp[8]={0};
-    sprintf(temp,"%04d",1900+p->tm_year);
-    currentTime.year=string(temp);
-	sprintf(temp,"%02d",1+p->tm_mon);
-	currentTime.month=string(temp);
-	sprintf(temp,"%02d",p->tm_mday);
-	currentTime.day=string(temp);
-	sprintf(temp,"%02d",p->tm_hour);
-	currentTime.hour=string(temp);
-	sprintf(temp,"%02d",p->tm_min);
-	currentTime.minute=string(temp);
-	sprintf(temp,"%02d",p->tm_sec);
-	currentTime.second=string(temp);
-	sprintf(temp,"%03d",tv.tv_usec/1000);
-	currentTime.millisecond = string(temp);
-    sprintf(temp, "%03d", tv.tv_usec % 1000);
-	currentTime.microsecond = string(temp);
-    sprintf(temp, "%d", p->tm_wday);
-    currentTime.weekDay = string(temp);
-#endif
-    return currentTime;
-}
-
-std::vector<std::string> SplitString(std::string str, std::string separator)
-{
-    std::string::size_type pos;
-    std::vector<std::string> result;
-    str+=separator;//扩展字符串以方便操作
-    int size=str.size();
-
-    for(int i=0; i<size; i++)
-    {
-        pos=str.find(separator,i);
-        if(pos<size)
-        {
-            std::string s=str.substr(i,pos-i);
-            result.push_back(s);
-            i=pos+separator.size()-1;
-        }
-    }
-    return result;
-}
-
-
 bool CompareConfidence(const ResultOfDetection &L,const ResultOfDetection &R)
 {
     return L.confidence > R.confidence;
@@ -109,7 +13,7 @@ bool CompareArea(const ResultOfDetection &L,const ResultOfDetection &R)
     return L.boundingBox.area() > R.boundingBox.area();
 }
 
-void NMS(vector<ResultOfDetection> &detections, float IOUThreshold)
+void NMS(std::vector<ResultOfDetection> &detections, float IOUThreshold)
 {
     // sort
     std::sort(detections.begin(), detections.end(), CompareConfidence);

Src/Utility/CommonUtility.h

@@ -3,23 +3,16 @@
 #ifndef __COMMON_UTILITY_H__
 #define __COMMON_UTILITY_H__
 
-#include <mutex>
-#include <string>
-#include <vector>
 #include <CommonDefinition.h>
 
-using namespace std;
-
 namespace migraphxSamples
 {
 
-// 分割字符串
-std::vector<std::string> SplitString(std::string str,std::string separator);
-
 // 排序规则: 按照置信度或者按照面积排序
 bool CompareConfidence(const ResultOfDetection &L,const ResultOfDetection &R);
 bool CompareArea(const ResultOfDetection &L,const ResultOfDetection &R);
 
+// 非极大抑制
 void NMS(std::vector<ResultOfDetection> &detections, float IOUThreshold);
 
 }

Src/Utility/Filesystem.cpp

@@ -11,12 +11,7 @@
 #include <unistd.h>
 #include <dirent.h>
 #endif
-#include <CommonUtility.h>
-#include <opencv2/opencv.hpp>
-#include <SimpleLog.h>
 
-using namespace cv;
- 
 // 路径分隔符(Linux:‘/’,Windows:’\\’)
 #ifdef _WIN32
 #define  PATH_SEPARATOR '\\'
@@ -24,9 +19,31 @@ using namespace cv;
 #define  PATH_SEPARATOR '/'
 #endif
 
+using namespace std;
+
 namespace migraphxSamples
 {
 
+static std::vector<std::string> SplitString(std::string str, std::string separator)
+{
+    std::string::size_type pos;
+    std::vector<std::string> result;
+    str+=separator;//扩展字符串以方便操作
+    int size=str.size();
+
+    for(int i=0; i<size; i++)
+    {
+        pos=str.find(separator,i);
+        if(pos<size)
+        {
+            std::string s=str.substr(i,pos-i);
+            result.push_back(s);
+            i=pos+separator.size()-1;
+        }
+    }
+    return result;
+}
+
 #if defined _WIN32 || defined WINCE
     const char dir_separators[] = "/\\";
 
@@ -293,7 +310,7 @@ namespace migraphxSamples
 		}
 		else
 		{
-			LOG_INFO(stdout, "could not open directory: %s", directory.c_str());
+			printf("could not open directory: %s", directory.c_str());
 		}
 	}
 
@@ -390,7 +407,7 @@ namespace migraphxSamples
 #endif
 			if (!result)
 			{
-				LOG_INFO(stdout, "can't remove directory: %s\n", path.c_str());
+				printf("can't remove directory: %s\n", path.c_str());
 			}
 		}
 		else
@@ -402,7 +419,7 @@ namespace migraphxSamples
 #endif
 			if (!result)
 			{
-				LOG_INFO(stdout, "can't remove file: %s\n", path.c_str());
+				printf("can't remove file: %s\n", path.c_str());
 			}
 		}
 	}
@@ -438,7 +455,7 @@ namespace migraphxSamples
 					{
 						RemoveAll(path);
 						++numberOfFiles;
-						LOG_INFO(stdout, "%s deleted! number of deleted files:%d\n", path.c_str(), numberOfFiles);
+						printf("%s deleted! number of deleted files:%d\n", path.c_str(), numberOfFiles);
 					}
 
 				}
@@ -452,7 +469,7 @@ namespace migraphxSamples
 		}
 		else
 		{
-			LOG_INFO(stdout, "could not open directory: %s", directory.c_str());
+			printf("could not open directory: %s", directory.c_str());
 		}
 
 		// ����RemoveAllɾ��Ŀ¼
@@ -592,17 +609,17 @@ namespace migraphxSamples
 
         if(!srcFile.is_open())
         {
-            LOG_ERROR(stdout,"can not open %s\n",srcPath.c_str());
+            printf("can not open %s\n",srcPath.c_str());
             return false;
         }
         if(!dstFile.is_open())
         {
-			LOG_ERROR(stdout, "can not open %s\n", dstPath.c_str());
+			printf("can not open %s\n", dstPath.c_str());
             return false;
         }
         if(srcPath==dstPath)
         {
-			LOG_ERROR(stdout, "src can not be same with dst\n");
+			printf("src can not be same with dst\n");
             return false;
         }
         char buffer[2048];
@@ -622,7 +639,7 @@ namespace migraphxSamples
     {
         if(srcPath==dstPath)
         {
-			LOG_ERROR(stdout, "src can not be same with dst\n");
+			printf("src can not be same with dst\n");
             return false;
         }
 
@@ -662,9 +679,9 @@ namespace migraphxSamples
 
 			// process
 			double process = (1.0*(i + 1) / fileNameList.size()) * 100;
-			LOG_INFO(stdout, "%s done! %f% \n", GetFileName(fileNameList[i]).c_str(), process);
+			printf("%s done! %f% \n", GetFileName(fileNameList[i]).c_str(), process);
         }
-		LOG_INFO(stdout, "all done!(the number of files:%d)\n", fileNameList.size());
+		printf("all done!(the number of files:%d)\n", fileNameList.size());
 
         return true;
 

Src/Utility/Filesystem.h

@@ -3,10 +3,8 @@
 #ifndef __FILE_SYSTEM_H__
 #define __FILE_SYSTEM_H__
 
-#include <vector>
 #include <string>
-
-using namespace std;
+#include <vector>
  
 namespace migraphxSamples
 {
@@ -21,7 +19,7 @@ bool IsDirectory(const std::string &path);
 bool IsPathSeparator(char c);
 
 // 路径拼接
-string JoinPath(const std::string &base, const std::string &path);
+std::string JoinPath(const std::string &base, const std::string &path);
 
 // 创建多级目录,注意：创建多级目录的时候，目标目录是不能有文件存在的
 bool CreateDirectories(const std::string &directoryPath);
@@ -49,14 +47,13 @@ void Remove(const std::string &directory, const std::string &extension="");
 /** 获取路径的文件名和扩展名
  * 
  *  示例：path为D:/1/1.txt,则GetFileName()为1.txt,GetFileName_NoExtension()为1,GetExtension()为.txt,GetParentPath()为D:/1/
-
 */
-string GetFileName(const std::string &path); // 1.txt
-string GetFileName_NoExtension(const std::string &path); // 1
-string GetExtension(const std::string &path);// .txt
-string GetParentPath(const std::string &path);// D:/1/
+std::string GetFileName(const std::string &path);
+std::string GetFileName_NoExtension(const std::string &path); 
+std::string GetExtension(const std::string &path);
+std::string GetParentPath(const std::string &path);
 
-// 拷贝文件:CopyFile("D:/1.txt","D:/2.txt");将1.txt拷贝为2.txt
+// 拷贝文件
 bool CopyFile(const std::string srcPath,const std::string dstPath);
 
 /** 拷贝目录

Src/Utility/SimpleLog.h

@@ -19,7 +19,7 @@ using namespace std;
 
 /** 简易日志
  * 
- * 轻量级日志系统，不依赖于其他第三方库，只需要包含一个头文件就可以使用。提供了4种日志级别，包括INFO,DEBUG,WARN和ERROR。
+ * 不依赖于其他第三方库，只需要包含一个头文件就可以使用。提供了4种日志级别，包括INFO,DEBUG,WARN和ERROR。
  * 
  * 示例1:
     // 初始化日志，在./Log/目录下创建两个日志文件log1.log和log2.log(注意：目录./Log/需要存在，否则日志创建失败)

Src/Detector/DetectorYOLOV5.cpp → Src/YOLOV5.cpp

-#include <DetectorYOLOV5.h>
+#include <YOLOV5.h>
+
 #include <migraphx/onnx.hpp>
 #include <migraphx/gpu/target.hpp>
-#include <migraphx/gpu/hip.hpp>
-#include <migraphx/generate.hpp>
 #include <migraphx/quantization.hpp>
-#include <opencv2/dnn.hpp>
-#include <CommonUtility.h>
+
 #include <Filesystem.h>
 #include <SimpleLog.h>
 
-using namespace cv::dnn;
 
 namespace migraphxSamples
 {
 
-DetectorYOLOV5::DetectorYOLOV5():logFile(NULL)
+DetectorYOLOV5::DetectorYOLOV5()
 {
 
 }
@@ -28,19 +25,24 @@ DetectorYOLOV5::~DetectorYOLOV5()
 
 ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializationParameterOfDetector)
 {
-    // 初始化(获取日志文件,加载配置文件等)
-    ErrorCode errorCode=DoCommonInitialization(initializationParameterOfDetector);
-    if(errorCode!=SUCCESS)
+    // 读取配置文件
+    std::string configFilePath=initializationParameterOfDetector.configFilePath;
+    if(Exists(configFilePath)==false)
     {
-        LOG_ERROR(logFile,"fail to DoCommonInitialization\n");
-        return errorCode;
+        LOG_ERROR(stdout, "no configuration file!\n");
+        return CONFIG_FILE_NOT_EXIST;
     }
-    LOG_INFO(logFile,"succeed to DoCommonInitialization\n");
+    if(!configurationFile.open(configFilePath, cv::FileStorage::READ))
+    {
+       LOG_ERROR(stdout, "fail to open configuration file\n");
+       return FAIL_TO_OPEN_CONFIG_FILE;
+    }
+    LOG_INFO(stdout, "succeed to open configuration file\n");
     
     // 获取配置文件参数
-    FileNode netNode = configurationFile["DetectorYOLOV5"];
-    string modelPath=initializationParameter.parentPath+(string)netNode["ModelPath"];
-    string pathOfClassNameFile=(string)netNode["ClassNameFile"];
+    cv::FileNode netNode = configurationFile["DetectorYOLOV5"];
+    std::string modelPath=(std::string)netNode["ModelPath"];
+    std::string pathOfClassNameFile=(std::string)netNode["ClassNameFile"];
     yolov5Parameter.confidenceThreshold = (float)netNode["ConfidenceThreshold"];
     yolov5Parameter.nmsThreshold = (float)netNode["NMSThreshold"];
     yolov5Parameter.objectThreshold = (float)netNode["ObjectThreshold"];
@@ -50,17 +52,21 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
     // 加载模型
     if(Exists(modelPath)==false)
     {
-        LOG_ERROR(logFile,"%s not exist!\n",modelPath.c_str());
+        LOG_ERROR(stdout,"%s not exist!\n",modelPath.c_str());
         return MODEL_NOT_EXIST;
     }
     net = migraphx::parse_onnx(modelPath);
-    LOG_INFO(logFile,"succeed to load model: %s\n",GetFileName(modelPath).c_str());
+    LOG_INFO(stdout,"succeed to load model: %s\n",GetFileName(modelPath).c_str());
 
     // 获取模型输入属性
-    std::pair<std::string, migraphx::shape> inputAttribute=*(net.get_parameter_shapes().begin());
-    inputName=inputAttribute.first;
-    inputShape=inputAttribute.second;
-    inputSize=cv::Size(inputShape.lens()[3],inputShape.lens()[2]);
+    std::unordered_map<std::string, migraphx::shape> inputMap=net.get_parameter_shapes();
+    inputName=inputMap.begin()->first;
+    inputShape=inputMap.begin()->second;
+    int N=inputShape.lens()[0];
+    int C=inputShape.lens()[1];
+    int H=inputShape.lens()[2];
+    int W=inputShape.lens()[3];
+    inputSize=cv::Size(W,H);
 
     // 设置模型为GPU模式
     migraphx::target gpuTarget = migraphx::gpu::target{};
@@ -74,20 +80,20 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
     // 编译模型
     migraphx::compile_options options;
     options.device_id=0; // 设置GPU设备，默认为0号设备
-    options.offload_copy=true; // 设置offload_copy
+    options.offload_copy=true;
     net.compile(gpuTarget,options);
-    LOG_INFO(logFile,"succeed to compile model: %s\n",GetFileName(modelPath).c_str());
+    LOG_INFO(stdout,"succeed to compile model: %s\n",GetFileName(modelPath).c_str());
 
-    // Run once by itself
-    migraphx::parameter_map inputData;
-    inputData[inputName]=migraphx::generate_argument(inputShape);
+    // warm up
+    std::unordered_map<std::string, migraphx::argument> inputData;
+    inputData[inputName]=migraphx::argument{inputShape};
     net.eval(inputData);
 
     // 读取类别名
     if(!pathOfClassNameFile.empty())
     {
-        ifstream classNameFile(pathOfClassNameFile);
-        string line;
+        std::ifstream classNameFile(pathOfClassNameFile);
+        std::string line;
         while (getline(classNameFile, line))
         {
             classNames.push_back(line);
@@ -99,12 +105,12 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
     }
 
     // log
-    LOG_INFO(logFile,"InputSize:%dx%d\n",inputSize.width,inputSize.height);
-    LOG_INFO(logFile,"InputName:%s\n",inputName.c_str());
-    LOG_INFO(logFile,"ConfidenceThreshold:%f\n",yolov5Parameter.confidenceThreshold);
-    LOG_INFO(logFile,"NMSThreshold:%f\n",yolov5Parameter.nmsThreshold);
-    LOG_INFO(logFile,"objectThreshold:%f\n",yolov5Parameter.objectThreshold);
-    LOG_INFO(logFile,"NumberOfClasses:%d\n",yolov5Parameter.numberOfClasses);
+    LOG_INFO(stdout,"InputSize:%dx%d\n",inputSize.width,inputSize.height);
+    LOG_INFO(stdout,"InputName:%s\n",inputName.c_str());
+    LOG_INFO(stdout,"ConfidenceThreshold:%f\n",yolov5Parameter.confidenceThreshold);
+    LOG_INFO(stdout,"NMSThreshold:%f\n",yolov5Parameter.nmsThreshold);
+    LOG_INFO(stdout,"objectThreshold:%f\n",yolov5Parameter.objectThreshold);
+    LOG_INFO(stdout,"NumberOfClasses:%d\n",yolov5Parameter.numberOfClasses);
 
     return SUCCESS;
 
@@ -114,21 +120,22 @@ ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDe
 {
     if(srcImage.empty()||srcImage.type()!=CV_8UC3)
     {
-        LOG_ERROR(logFile, "image error!\n");
+        LOG_ERROR(stdout, "image error!\n");
         return IMAGE_ERROR;
     }
 
-   // 预处理并转换为NCHW
+    // 数据预处理并转换为NCHW格式
     cv::Mat inputBlob;
-    blobFromImage(srcImage,
+    cv::dnn::blobFromImage(srcImage,
                     inputBlob,
                     1 / 255.0,
                     inputSize,
-                    Scalar(0, 0, 0),
+                    cv::Scalar(0, 0, 0),
                     true,
                     false);
-    // 输入数据
-    migraphx::parameter_map inputData;
+
+    // 创建输入数据
+    std::unordered_map<std::string, migraphx::argument> inputData;
     inputData[inputName]= migraphx::argument{inputShape, (float*)inputBlob.data};
 
     // 推理
@@ -192,7 +199,7 @@ ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDe
 
     //执行non maximum suppression消除冗余重叠boxes
     std::vector<int> indices;
-    dnn::NMSBoxes(boxes, confidences, yolov5Parameter.confidenceThreshold, yolov5Parameter.nmsThreshold, indices);
+    cv::dnn::NMSBoxes(boxes, confidences, yolov5Parameter.confidenceThreshold, yolov5Parameter.nmsThreshold, indices);
     for (size_t i = 0; i < indices.size(); ++i)
     {
         int idx = indices[i];
@@ -212,39 +219,4 @@ ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDe
     return SUCCESS;
 }
 
-ErrorCode DetectorYOLOV5::DoCommonInitialization(InitializationParameterOfDetector initializationParameterOfDetector)
-{
-    initializationParameter=initializationParameterOfDetector;
-
-    // 获取日志文件
-    logFile=LogManager::GetInstance()->GetLogFile(initializationParameter.logName);
-
-    // 加载配置文件
-    std::string configFilePath=initializationParameter.configFilePath;
-    if(!Exists(configFilePath))
-    {
-        LOG_ERROR(logFile, "no configuration file!\n");
-        return CONFIG_FILE_NOT_EXIST;
-    }
-    if(!configurationFile.open(configFilePath, FileStorage::READ))
-    {
-       LOG_ERROR(logFile, "fail to open configuration file\n");
-       return FAIL_TO_OPEN_CONFIG_FILE;
-    }
-    LOG_INFO(logFile, "succeed to open configuration file\n");
-
-    // 修改父路径
-    std::string &parentPath = initializationParameter.parentPath;
-    if (!parentPath.empty())
-    {
-        if(!IsPathSeparator(parentPath[parentPath.size() - 1]))
-        {
-           parentPath+=PATH_SEPARATOR;
-        }
-    }
-
-    return SUCCESS;
-
-}
-
 }

Src/Detector/DetectorYOLOV5.h → Src/YOLOV5.h

 #ifndef __DETECTOR_YOLOV5_H__
 #define __DETECTOR_YOLOV5_H__
 
-#include <string>
 #include <migraphx/program.hpp>
-#include <opencv2/opencv.hpp>
-#include <CommonDefinition.h>
 
-using namespace std;
-using namespace cv;
-using namespace migraphx;
+#include <CommonDefinition.h>
 
 namespace migraphxSamples
 {
@@ -33,21 +28,16 @@ public:
 
     ErrorCode Detect(const cv::Mat &srcImage, std::vector<ResultOfDetection> &resultsOfDetection);
 
-private:
-    ErrorCode DoCommonInitialization(InitializationParameterOfDetector initializationParameterOfDetector);
-
 private:
     cv::FileStorage configurationFile;
-    InitializationParameterOfDetector initializationParameter;
-    FILE *logFile;
 
     migraphx::program net;
     cv::Size inputSize;
-    string inputName;
+    std::string inputName;
     migraphx::shape inputShape;
     
     bool useFP16;
-    vector<string> classNames;
+    std::vector<std::string> classNames;
 
     YOLOV5Parameter yolov5Parameter;
 };

Src/main.cpp

 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <Sample.h>
+#include <SimpleLog.h>
+#include <Filesystem.h>
+#include <YOLOV5.h>
 
-void MIGraphXSamplesUsage(char* programName)
+int main()
 {
-    printf("Usage : %s <index> \n", programName);
-    printf("index:\n");
-    printf("\t 0) YOLOV5 sample.\n");
-}
-
-int main(int argc, char *argv[])
-{
-    if (argc < 2 || argc > 2)
+    // 创建YOLOV5检测器
+    migraphxSamples::DetectorYOLOV5 detector;
+    migraphxSamples::InitializationParameterOfDetector initParamOfDetectorYOLOV5;
+    initParamOfDetectorYOLOV5.configFilePath = CONFIG_FILE;
+    migraphxSamples::ErrorCode errorCode=detector.Initialize(initParamOfDetectorYOLOV5);
+    if(errorCode!=migraphxSamples::SUCCESS)
     {
-        MIGraphXSamplesUsage(argv[0]);
-        return -1;
+        LOG_ERROR(stdout, "fail to initialize detector!\n");
+        exit(-1);
     }
-    if (!strncmp(argv[1], "-h", 2))
-    {
-        MIGraphXSamplesUsage(argv[0]);
-        return 0;
-    }
-    switch (*argv[1])
+    LOG_INFO(stdout, "succeed to initialize detector\n");
+
+    // 读取测试图片
+    cv::Mat srcImage = cv::imread("../Resource/Images/bus.jpg",1);
+
+    // 推理
+    std::vector<migraphxSamples::ResultOfDetection> predictions;
+    double time1 = cv::getTickCount();
+    detector.Detect(srcImage,predictions);
+    double time2 = cv::getTickCount();
+    double elapsedTime = (time2 - time1)*1000 / cv::getTickFrequency();
+    LOG_INFO(stdout, "inference time:%f ms\n", elapsedTime);
+
+    // 获取推理结果
+    LOG_INFO(stdout,"========== Detection Results ==========\n");
+    for(int i=0;i<predictions.size();++i)
     {
-        case '0':
-            {
-                Sample_DetectorYOLOV5();
-                break;
-            }
-        default :
-            {
-                MIGraphXSamplesUsage(argv[0]);
-                break;
-            }
+        migraphxSamples::ResultOfDetection result=predictions[i];
+        cv::rectangle(srcImage,result.boundingBox,cv::Scalar(0,255,255),2);
+
+        LOG_INFO(stdout,"box:%d %d %d %d,label:%d,confidence:%f\n",predictions[i].boundingBox.x,
+        predictions[i].boundingBox.y,predictions[i].boundingBox.width,predictions[i].boundingBox.height,predictions[i].classID,predictions[i].confidence);
     }
+    cv::imwrite("Result.jpg",srcImage);
+    LOG_INFO(stdout,"Detection results have been saved to ./Result.jpg\n");
+
     return 0;
 }
\ No newline at end of file