更新示例工程

Doc/Tutorial_Cpp.md

@@ -21,10 +21,21 @@ ErrorCode DetectorYOLOV3::Initialize(InitializationParameterOfDetector initializ
     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();
-    inputName=inputAttribute.first;
-    inputShape=inputAttribute.second;
+   // 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];
     int C=inputShape.lens()[1];
     int H=inputShape.lens()[2];
@@ -109,6 +120,18 @@ ErrorCode DetectorYOLOV3::Detect(const cv::Mat &srcImage, std::vector<ResultOfDe
 }
 ```
 
+另外，如果想要指定输出节点，可以在eval()方法中通过提供outputNames参数来实现：
+
+```
+...
+// 推理
+std::vector<std::string> outputNames = {"187","121","output"}
+std::vector<migraphx::argument> inferenceResults = net.eval(inputData, outputNames);
+...
+```
+
+如果没有指定outputName参数，则默认输出所有输出节点，此时输出节点的顺序与ONNX中输出节点顺序保持一致，可以通过netron查看ONNX文件的输出节点的顺序。  
+
 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；

Doc/Tutorial_Python.md

@@ -49,11 +49,22 @@ class YOLOv3:
         # 解析推理模型
         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 = self.model.get_parameter_names()[0]
+        self.inputName = "images"
 
         # 获取模型的输入尺寸
-        inputShape = self.model.get_parameter_shapes()[self.inputName].lens()
+        inputShape = inputShape=inputs[self.inputName].lens()
         self.inputHeight = int(inputShape[2])
         self.inputWidth = int(inputShape[3])
 ```

Python/YoloV3_infer_migraphx.py

@@ -19,11 +19,22 @@ class YOLOv3:
         # 解析推理模型
         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 = self.model.get_parameter_names()[0]
+        self.inputName = "images"
 
         # 获取模型的输入尺寸
-        inputShape = self.model.get_parameter_shapes()[self.inputName].lens()
+        inputShape = inputShape=inputs[self.inputName].lens()
         self.inputHeight = int(inputShape[2])
         self.inputWidth = int(inputShape[3])
         print("inputName:{0} \ninputShape:{1}".format(self.inputName, inputShape))

Src/YOLOV3.cpp

@@ -55,10 +55,21 @@ ErrorCode DetectorYOLOV3::Initialize(InitializationParameterOfDetector initializ
     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::unordered_map<std::string, migraphx::shape> inputMap=net.get_parameter_shapes();
-    inputName=inputMap.begin()->first;
-    inputShape=inputMap.begin()->second;
+    // 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];
     int C=inputShape.lens()[1];
     int H=inputShape.lens()[2];