修改yolov3工程格式

Doc/Tutorial_Cpp.md

@@ -22,18 +22,8 @@ ErrorCode DetectorYOLOV3::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];
@@ -53,7 +43,7 @@ ErrorCode DetectorYOLOV3::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.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());
@@ -77,13 +67,13 @@ ErrorCode DetectorYOLOV3::Detect(const cv::Mat &srcImage, std::vector<ResultOfDe
 
     // 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,  //YOLOV3输入尺寸，本示例为416x416
-                    Scalar(0, 0, 0),  //未减去均值
-                    true,  //转换RB通道
-                    false);
+    blobFromImage(srcImage,         // 输入数据
+                  inputBlob,        // 输出数据
+                  1 / 255.0,        // 归一化
+                  inputSize,        // YOLOV3输入尺寸，本示例为416x416
+                  Scalar(0, 0, 0),  // 未减去均值
+                  true,             // 转换RB通道
+                  false);
                     
     ...
 }

Doc/Tutorial_Python.md

@@ -50,18 +50,11 @@ class YOLOv3:
         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()
@@ -80,12 +73,10 @@ def detect(self, 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)
 

Python/YoloV3_infer_migraphx.py

@@ -20,18 +20,11 @@ class YOLOv3:
         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()
@@ -45,12 +38,10 @@ class YOLOv3:
 
         # 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)
 

Src/YOLOV3.cpp

@@ -15,16 +15,14 @@ DetectorYOLOV3::DetectorYOLOV3()
 
 DetectorYOLOV3::~DetectorYOLOV3()
 {
-
     configurationFile.release();
-    
 }
 
 ErrorCode DetectorYOLOV3::Initialize(InitializationParameterOfDetector initializationParameterOfDetector)
 {
     // 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;
@@ -47,7 +45,7 @@ ErrorCode DetectorYOLOV3::Initialize(InitializationParameterOfDetector initializ
     useFP16=(bool)(int)netNode["UseFP16"];
 
     // 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;
@@ -56,18 +54,8 @@ ErrorCode DetectorYOLOV3::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];

Src/main.cpp

@@ -24,11 +24,7 @@ int main()
 
     // 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");