提交YOLOV5 C++推理示例

.gitignore

+# This file is used to ignore files which are generated
+# ----------------------------------------------------------------------------
+
+build/*
+depend/*
+.vscode/*
+core.*
+
+# qtcreator generated files
+*.pro.user*
+
+# VS
+*.sdf
+*.opensdf
+*.ilk
+*.pdb
+*.exp
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+
+# Fortran module files
+*.mod
+*.smod
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+
+# Executables
+*.exe
+*.out
+*.app
+
+# xemacs temporary files
+*.flc
+
+# Vim temporary files
+.*.swp
+
+# others
+*.avi
+*.pyc
+*.egg

3rdParty/InstallOpenCVDependences.sh

+#! /bin/sh
+
+############### Ubuntu  ###############
+# 参考：https://docs.opencv.org/3.4.11/d7/d9f/tutorial_linux_install.html
+# apt-get install build-essential -y
+# apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev -y
+# apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev -y # 处理图像所需的包，可选
+
+############### CentOS ###############
+yum install gcc gcc-c++ gtk2-devel gimp-devel gimp-devel-tools gimp-help-browser zlib-devel libtiff-devel libjpeg-devel libpng-devel gstreamer-devel libavc1394-devel libraw1394-devel libdc1394-devel jasper-devel jasper-utils swig python libtool nasm -y
\ No newline at end of file

3rdParty/InstallRBuild.sh

+
+############################ 在线安装依赖 ###############################
+#cd ./3rdParty
+#pip install rbuild-master.tar.gz
+
+
+############################ 离线安装依赖 ###############################
+# 安装依赖
+cd ./3rdParty/rbuild_depend
+pip install click-6.6-py2.py3-none-any.whl
+pip install six-1.15.0-py2.py3-none-any.whl
+pip install subprocess32-3.5.4.tar.gz
+pip install cget-0.1.9.tar.gz
+
+# 安装rbuild
+cd ../
+pip install rbuild-master.tar.gz
+
+

CMakeLists.txt

+# 设置cmake的最低版本
+cmake_minimum_required(VERSION 3.5)
+
+# 设置项目名
+project(MIGraphX_Samples)
+
+# 设置编译器
+set(CMAKE_CXX_COMPILER g++)
+set(CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS} -std=c++17) # 2.2版本以上需要c++17
+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})
+
+# 添加依赖库路径
+set(LIBRARY_PATH ${CMAKE_CURRENT_SOURCE_DIR}/depend/lib64/
+                $ENV{DTKROOT}/lib/)
+link_directories(${LIBRARY_PATH})
+
+# 添加依赖库
+set(LIBRARY opencv_core
+            opencv_imgproc
+            opencv_imgcodecs
+            opencv_dnn
+            migraphx_ref
+            migraphx
+            migraphx_c
+            migraphx_device
+            migraphx_gpu
+            migraphx_onnx)
+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/Utility/CommonUtility.cpp
+                ${CMAKE_CURRENT_SOURCE_DIR}/Src/Utility/Filesystem.cpp)
+
+# 添加可执行目标
+add_executable(MIGraphX_Samples ${SOURCE_FILES})

YoloV5_infer_migraphx.py → 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('./weights/coco.names', 'r').readlines()))
+        self.classNames = list(map(lambda x: x.strip(), open('../Resource/Models/Detector/YOLOV5/coco.names', 'r').readlines()))
 
         # 解析推理模型
         self.model = migraphx.parse_onnx(path)
@@ -118,8 +118,8 @@ class YOLOv5:
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument('--imgpath', type=str, default='./images/bus.jpg', help="image path")
-    parser.add_argument('--modelpath', type=str, default='./weights/yolov5s.onnx', help="onnx filepath")
+    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('--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')

Python/requirements.txt

+opencv-contrib-python
+numpy
+os
+argparse
+time
\ No newline at end of file

README.md

@@ -13,27 +13,83 @@ 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。
 
-## 推理
+## 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：
 
-### 环境配置
+```python
+docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
+```
 
-在[光源](https://www.sourcefind.cn/#/image/dcu/custom)可拉取用于推理的docker镜像，YoloV5模型推理推荐的镜像如下：
+### 安装Opencv依赖
 
+```python
+cd <path_to_migraphx_samples>
+sh ./3rdParty/InstallOpenCVDependences.sh
 ```
-docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort_dcu_1.14.0_migraphx2.5.2_dtk22.10.1
+
+### 修改CMakeLists.txt
+
+- 如果使用ubuntu系统，需要修改CMakeLists.txt中依赖库路径：
+  将"${CMAKE_CURRENT_SOURCE_DIR}/depend/lib64/"修改为"${CMAKE_CURRENT_SOURCE_DIR}/depend/lib/"
+
+- **MIGraphX2.3.0及以上版本需要c++17**
+
+
+### 安装OpenCV并构建工程
+
 ```
+rbuild build -d depend
+```
+
+### 设置环境变量
 
-在[光合开发者社区](https://cancon.hpccube.com:65024/4/main/)可下载MIGraphX安装包，python依赖安装：
+将依赖库依赖加入环境变量LD_LIBRARY_PATH，在~/.bashrc中添加如下语句：
+
+**Centos**:
 
 ```
-pip install -r requirements.txt
+export LD_LIBRARY_PATH=<path_to_migraphx_samples>/depend/lib64/:$LD_LIBRARY_PATH
+```
+
+**Ubuntu**:
+
+```
+export LD_LIBRARY_PATH=<path_to_migraphx_samples>/depend/lib/:$LD_LIBRARY_PATH
 ```
 
-### 运行示例
+然后执行:
+
+```
+source ~/.bashrc
+```
+
+## 推理
+
+### C++版本推理
+
+成功编译YoloV5工程后，在build目录下输入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%;" />
+
+### 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 \
@@ -44,7 +100,7 @@ python YoloV5_infer_migraphx.py \
 
 程序运行结束会在当前目录生成YoloV5检测结果图像。
 
-<img src="./images/Result.jpg" alt="Result" style="zoom: 50%;" />
+<img src="./Resource/Images/Result.jpg" alt="Result_2" style="zoom: 50%;" />
 
 ## 历史版本
 

Resource/Configuration.xml

+<?xml version="1.0" encoding="GB2312"?>
+<opencv_storage>
+
+	<!--YOLOV5检测器 -->
+	<DetectorYOLOV5>
+		<ModelPath>"../Resource/Models/Detector/YOLOV5/yolov5s.onnx"</ModelPath>
+		<ClassNameFile>"../Resource/Models/Detector/YOLOV5/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>
+	</DetectorYOLOV5>
+
+</opencv_storage>

Src/Detector/DetectorYOLOV5.cpp

+#include <DetectorYOLOV5.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()
+{
+
+    configurationFile.release();
+    
+}
+
+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)
+    {
+        LOG_ERROR(logFile,"fail to DoCommonInitialization\n");
+        return errorCode;
+    }
+    LOG_INFO(logFile,"succeed to DoCommonInitialization\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"];
+    yolov5Parameter.confidenceThreshold = (float)netNode["ConfidenceThreshold"];
+    yolov5Parameter.nmsThreshold = (float)netNode["NMSThreshold"];
+    yolov5Parameter.objectThreshold = (float)netNode["ObjectThreshold"];
+    yolov5Parameter.numberOfClasses=(int)netNode["NumberOfClasses"];
+    useFP16=(bool)(int)netNode["UseFP16"];
+
+    // 加载模型
+    if(Exists(modelPath)==false)
+    {
+        LOG_ERROR(logFile,"%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());
+
+    // 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]);
+
+    // 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(logFile,"succeed to compile model: %s\n",GetFileName(modelPath).c_str());
+
+    // Run once by itself
+    migraphx::parameter_map inputData;
+    inputData[inputName]=migraphx::generate_argument(inputShape);
+    net.eval(inputData);
+
+    // 读取类别名
+    if(!pathOfClassNameFile.empty())
+    {
+        ifstream classNameFile(pathOfClassNameFile);
+        string line;
+        while (getline(classNameFile, line))
+        {
+            classNames.push_back(line);
+        }
+    }
+    else
+    {
+        classNames.resize(yolov5Parameter.numberOfClasses);
+    }
+
+    // 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);
+
+    return SUCCESS;
+
+}
+
+ErrorCode DetectorYOLOV5::Detect(const cv::Mat &srcImage, std::vector<ResultOfDetection> &resultsOfDetection)
+{
+    if(srcImage.empty()||srcImage.type()!=CV_8UC3)
+    {
+        LOG_ERROR(logFile, "image error!\n");
+        return IMAGE_ERROR;
+    }
+
+   // 预处理并转换为NCHW
+    cv::Mat inputBlob;
+    blobFromImage(srcImage,
+                    inputBlob,
+                    1 / 255.0,
+                    inputSize,
+                    Scalar(0, 0, 0),
+                    true,
+                    false);
+    // 输入数据
+    migraphx::parameter_map 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);
+
+    //获取先验框的个数
+    int numProposal = outs[0].size[1];
+    int numOut = outs[0].size[2];
+    //变换输出的维度
+    outs[0] = outs[0].reshape(0, numProposal);
+
+    //生成先验框
+    std::vector<float> confidences;
+    std::vector<cv::Rect> boxes;
+    std::vector<int> classIds;
+    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++)
+    {
+        float boxScores = pdata[4];
+        if (boxScores > yolov5Parameter.objectThreshold)
+        {
+            cv::Mat scores = outs[0].row(rowInd).colRange(5, numOut);
+            cv::Point classIdPoint;
+            double maxClassScore;
+            cv::minMaxLoc(scores, 0, &maxClassScore, 0, &classIdPoint);
+            maxClassScore *= boxScores;
+            if (maxClassScore > yolov5Parameter.confidenceThreshold)
+            {
+                const int classIdx = classIdPoint.x;
+                float cx = pdata[0] * ratiow;
+                float cy = pdata[1] * ratioh;
+                float w = pdata[2] * ratiow;
+                float h = pdata[3] * ratioh;
+
+                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;
+    }
+
+    //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);
+    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];
+
+        ResultOfDetection result;
+        result.boundingBox=box;
+        result.confidence=confidence;// confidence
+        result.classID=classID; // label
+        result.className=className;
+        resultsOfDetection.push_back(result);
+    }
+
+    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

+#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;
+
+namespace migraphxSamples
+{
+
+typedef struct _YOLOV5Parameter
+{
+    int numberOfClasses;
+    float confidenceThreshold;
+    float nmsThreshold;
+    float objectThreshold;
+
+}YOLOV5Parameter;
+
+class DetectorYOLOV5
+{
+public:
+    DetectorYOLOV5();
+    
+    ~DetectorYOLOV5();
+
+    ErrorCode Initialize(InitializationParameterOfDetector initializationParameterOfDetector);
+
+    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;
+    migraphx::shape inputShape;
+    
+    bool useFP16;
+    vector<string> classNames;
+
+    YOLOV5Parameter yolov5Parameter;
+};
+
+}
+
+
+#endif
+