修改yolov5工程格式

Doc/Tutorial_Python.md

@@ -54,18 +54,11 @@ class YOLOv5:
             self.model = migraphx.parse_onnx(path, map_input_dims=maxInput)
             
              # 获取模型输入/输出节点信息
-            print("inputs:")
             inputs = self.model.get_inputs()
-            for key,value in inputs.items():
-                print("{}:{}".format(key,value))
-            
-            print("outputs:")
             outputs = self.model.get_outputs()
-            for key,value in outputs.items():
-                print("{}:{}".format(key,value))
 
             # 获取模型的输入name
-            self.inputName = "images"
+            self.inputName = self.model.get_parameter_names()[0]
             
             # 获取模型的输入尺寸
             inputShape = inputShape=inputs[self.inputName].lens()

Python/YoloV5_infer_migraphx.py

@@ -22,18 +22,11 @@ class YOLOv5:
             self.model = migraphx.parse_onnx(path, map_input_dims=maxInput)
 
             # 获取模型输入/输出节点信息
-            print("inputs:")
             inputs = self.model.get_inputs()
-            for key,value in inputs.items():
-                print("{}:{}".format(key,value))
-            
-            print("outputs:")
             outputs = self.model.get_outputs()
-            for key,value in outputs.items():
-                print("{}:{}".format(key,value))
 
             # 获取模型的输入name
-            self.inputName = "images"
+            self.inputName = self.model.get_parameter_names()[0]
             
             # 获取模型的输入尺寸
             inputShape = inputShape=inputs[self.inputName].lens()
@@ -43,18 +36,11 @@ class YOLOv5:
         else:
             self.model = migraphx.parse_onnx(path) 
             # 获取模型输入/输出节点信息
-            print("inputs:")
             inputs = self.model.get_inputs()
-            for key,value in inputs.items():
-                print("{}:{}".format(key,value))
-            
-            print("outputs:")
             outputs = self.model.get_outputs()
-            for key,value in outputs.items():
-                print("{}:{}".format(key,value))
 
             # 获取模型的输入name
-            self.inputName = "images"
+            self.inputName = self.model.get_parameter_names()[0]
 
             # 获取模型的输入尺寸
             inputShape = inputShape=inputs[self.inputName].lens()
@@ -64,7 +50,6 @@ class YOLOv5:
         
         # 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")
 
     def detect(self, image, input_shape=None):
         if(self.isDynamic):
@@ -74,9 +59,8 @@ class YOLOv5:
         input_img = self.prepare_input(image)
 
         # 执行推理
-        start = time.time()
         result = self.model.run({self.inputName: 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)
 
@@ -211,6 +195,7 @@ if __name__ == '__main__':
     # 静态推理
     if args.staticInfer:
         yolov5_Static(args.imgPath, args.staticModelPath, args.objectThreshold, args.confThreshold, args.nmsThreshold)
+        
     # 动态推理
     if args.dynamicInfer:
         yolov5_dynamic(args.imgFolderPath, args.dynamicModelPath, args.objectThreshold, args.confThreshold, args.nmsThreshold)

Src/YOLOV5.cpp

@@ -16,16 +16,14 @@ DetectorYOLOV5::DetectorYOLOV5()
 
 DetectorYOLOV5::~DetectorYOLOV5()
 {
-
     configurationFile.release();
-    
 }
 
 ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializationParameterOfDetector, bool dynamic)
 {
     // 读取配置文件
     std::string configFilePath=initializationParameterOfDetector.configFilePath;
-    if(Exists(configFilePath)==false)
+    if(!Exists(configFilePath))
     {
         LOG_ERROR(stdout, "no configuration file!\n");
         return CONFIG_FILE_NOT_EXIST;
@@ -57,7 +55,7 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
     if(dynamic)
     {
         // 加载模型
-        if(Exists(modelPath)==false)
+        if(!Exists(modelPath))
         {
             LOG_ERROR(stdout,"%s not exist!\n",modelPath.c_str());
             return MODEL_NOT_EXIST;
@@ -69,18 +67,8 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
         LOG_INFO(stdout,"succeed to load model: %s\n",GetFileName(modelPath).c_str());
 
         // 获取模型输入/输出节点信息
-        std::cout<<"inputs:"<<std::endl;
         std::unordered_map<std::string, migraphx::shape> inputs=net.get_inputs();
-        for(auto i:inputs)
-        {
-            std::cout<<i.first<<":"<<i.second<<std::endl;
-        }
-        std::cout<<"outputs:"<<std::endl;
         std::unordered_map<std::string, migraphx::shape> outputs=net.get_outputs();
-        for(auto i:outputs)
-        {
-            std::cout<<i.first<<":"<<i.second<<std::endl;
-        }
         inputName=inputs.begin()->first;
         inputShape=inputs.begin()->second;
         int N=inputShape.lens()[0];
@@ -95,7 +83,7 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
     else
     {
         // 加载模型
-        if(Exists(modelPath)==false)
+        if(!Exists(modelPath))
         {
             LOG_ERROR(stdout,"%s not exist!\n",modelPath.c_str());
             return MODEL_NOT_EXIST;
@@ -104,18 +92,8 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
         LOG_INFO(stdout,"succeed to load model: %s\n",GetFileName(modelPath).c_str());
 
         // 获取模型输入/输出节点信息
-        std::cout<<"inputs:"<<std::endl;
         std::unordered_map<std::string, migraphx::shape> inputs=net.get_inputs();
-        for(auto i:inputs)
-        {
-            std::cout<<i.first<<":"<<i.second<<std::endl;
-        }
-        std::cout<<"outputs:"<<std::endl;
         std::unordered_map<std::string, migraphx::shape> outputs=net.get_outputs();
-        for(auto i:outputs)
-        {
-            std::cout<<i.first<<":"<<i.second<<std::endl;
-        }
         inputName=inputs.begin()->first;
         inputShape=inputs.begin()->second;
         int N=inputShape.lens()[0];
@@ -170,9 +148,7 @@ ErrorCode DetectorYOLOV5::Initialize(InitializationParameterOfDetector initializ
         classNames.resize(yolov5Parameter.numberOfClasses);
     }
 
-
     return SUCCESS;
-
 }
 
 ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<std::size_t> &relInputShape, std::vector<ResultOfDetection> &resultsOfDetection, bool dynamic)

Src/main.cpp

@@ -71,11 +71,7 @@ void Sample_YOLOV5()
     
     // 推理
     std::vector<migraphxSamples::ResultOfDetection> predictions;
-    double time1 = cv::getTickCount();
     detector.Detect(srcImage,inputShape,predictions,false);
-    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");
@@ -135,11 +131,7 @@ void Sample_YOLOV5_Dynamic()
     {
         // 推理
         std::vector<migraphxSamples::ResultOfDetection> predictions;
-        double time1 = cv::getTickCount();
         detector.Detect(srcImages[i], inputShapes[i], predictions, true);
-        double time2 = cv::getTickCount();
-        double elapsedTime = (time2 - time1)*1000 / cv::getTickFrequency();
-        LOG_INFO(stdout, "inference image%d time:%f ms\n", i, elapsedTime);
 
         // 获取推理结果
         LOG_INFO(stdout,"========== Detection Image%d Results ==========\n", i);