提交RetinaFace C++示例

README.md

@@ -12,35 +12,89 @@ RetinaFace模型 有几个主要特点：
 - 引入 SSH 算法的 Context Modeling；
 - 多任务训练，提供额外的监督信息。
 
-## 推理
+## 构建安装
+
+在光源可拉取推理的docker镜像，RetinaFace工程推荐的镜像如下：
+
+```python
+docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
+```
+
+### 安装Opencv依赖
+
+```python
+cd <path_to_migraphx_samples>
+sh ./3rdParty/InstallOpenCVDependences.sh
+```
+
+### 修改CMakeLists.txt
 
-### 环境配置
+- 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/"
 
-在[光源](https://www.sourcefind.cn/#/image/dcu/custom)可拉取用于推理的docker镜像，RetinaFace 模型推理推荐的镜像如下：
+- **MIGraphX2.3.0及以上版本需要c++17**
+
+
+### 安装OpenCV并构建工程
 
 ```
-docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort_dcu_1.14.0_migraphx2.5.2_dtk22.10.1
+rbuild build -d depend
 ```
 
-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：
+### 设置环境变量
+
+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
+```
+
+然后执行:
+
+```
+source ~/.bashrc
+```
+
+## 推理
+
+### C++版本推理
 
-安装DTK版的Pytorch和torchvision，下载地址：https://cancon.hpccube.com:65024/4/main/pytorch，https://cancon.hpccube.com:65024/4/main/vision
+成功编译RetinaFace工程后，在build目录下输入如下命令运行该示例：
 
-### 运行示例
+```
+./MIGraphX_Samples 0
+```
+
+程序运行结束会在build目录生成RetinaFace人脸检测结果图像。
+
+<img src="./Resource/Images/Result_1.jpg" alt="Result" style="zoom:67%;" />
 
-RetinaFace模型的推理示例程序是RetinaFace_infer_migraphx.py，使用如下命令运行该推理示例：
+### python版本推理
+
+RetinaFace模型的推理示例程序是RetinaFace_infer_migraphx.py，进入python文件夹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 RetinaFace_infer_migraphx.py 
 ```
 
 程序运行结束会在当前目录生成RetinaFace检测结果图像。
 
-<img src="./curve/Result.jpg" alt="Result" style="zoom: 50%;" />
+<img src="./Resource/Images/Result_2.jpg" alt="Result_2" style="zoom:67%;" />
 
 ## 历史版本
 

Resource/Configuration.xml

+<?xml version="1.0" encoding="GB2312"?>
+<opencv_storage>
+
+	<!--RetinaFace检测器-->
+	<DetectorRetinaFace>
+		<ModelPath>"../Resource/Models/Detector/RetinaFace/mobilenet0.25_Final.onnx"</ModelPath>
+        <Scale>1.0</Scale><!--缩放尺度-->
+		<MeanValue1>104</MeanValue1><!--均值，顺序为bgr-->
+		<MeanValue2>117</MeanValue2>
+		<MeanValue3>123</MeanValue3>
+		<SwapRB>0</SwapRB>
+		<Crop>0</Crop>
+		<UseInt8>0</UseInt8><!--是否使用int8,不支持-->
+		<UseFP16>0</UseFP16><!--是否使用FP16-->
+
+		<!--////////////////// RetinaFace检测器参数 ////////////////// -->
+		<!--priorbox层的个数-->
+		<PriorBoxLayerNumber>3</PriorBoxLayerNumber>
+
+		<!--每个priorbox层的minisize和maxSize(需要与输出检测层顺序保持一致，下面涉及每个priorbox层参数的都需要保持顺序一致)-->
+		<MinSize11>16</MinSize11>
+		<MinSize12>32</MinSize12>
+		<MinSize21>64</MinSize21>
+		<MinSize22>128</MinSize22>
+		<MinSize31>256</MinSize31>
+		<MinSize32>512</MinSize32>
+
+		<!--每个priorbox层的Flip和Clip(使用0,1表示)-->
+		<Flip1>0</Flip1>
+		<Flip2>0</Flip2>
+		<Flip3>0</Flip3>
+
+		<Clip1>0</Clip1>
+		<Clip2>0</Clip2>
+		<Clip3>0</Clip3>
+
+		<!--每个priorbox层的宽高比(由于RetinaFace只包含宽高比为1的anchor，所以这里不需要设置宽高比)-->
+		<!-- <AspectRatio11>0.3333</AspectRatio11>
+		<AspectRatio12>0.25</AspectRatio12>
+		<AspectRatio21>0.3333</AspectRatio21>
+		<AspectRatio22>0.25</AspectRatio22>
+		<AspectRatio31>0.3333</AspectRatio31>
+		<AspectRatio32>0.25</AspectRatio32>
+		<AspectRatio41>0.3333</AspectRatio41>
+		<AspectRatio42>0.25</AspectRatio42> -->
+
+		<!--每个priorbox层的step-->
+		<PriorBoxStepWidth1>8</PriorBoxStepWidth1><!--第一个priorbox层的step的width-->
+		<PriorBoxStepWidth2>16</PriorBoxStepWidth2>
+		<PriorBoxStepWidth3>32</PriorBoxStepWidth3>
+
+		<PriorBoxStepHeight1>8</PriorBoxStepHeight1><!--第一个priorbox层的step的height-->
+		<PriorBoxStepHeight2>16</PriorBoxStepHeight2>
+		<PriorBoxStepHeight3>32</PriorBoxStepHeight3>
+
+		<!--priorbox层中的offset-->
+		<Offset>0.5</Offset>
+
+		<!--DetectionOutput参数-->
+		<ClassNumber>2</ClassNumber>
+		<TopK>400</TopK>
+		<KeepTopK>200</KeepTopK>
+		<NMSThreshold>0.3</NMSThreshold>
+		<ConfidenceThreshold>0.9</ConfidenceThreshold>
+	</DetectorRetinaFace>
+</opencv_storage>

Src/RetinaFace/DetectorRetinaFace.h

+#ifndef __DETECTOR_RETINAFACE_H__
+#define __DETECTOR_RETINAFACE_H__
+
+#include <string>
+#include <migraphx/program.hpp>
+#include <opencv2/opencv.hpp>
+#include <CommonDefinition.h>
+#include <SSDDefinition.h>
+
+using namespace std;
+using namespace cv;
+using namespace migraphx;
+
+namespace migraphxSamples
+{
+
+class DetectorRetinaFace
+{
+public:
+    DetectorRetinaFace();
+    
+    ~DetectorRetinaFace();
+
+    ErrorCode Initialize(InitializationParameterOfDetector initializationParameterOfDetector);
+
+    ErrorCode Detect(const cv::Mat &srcImage,std::vector<ResultOfDetection> &resultsOfDetection);
+
+private:
+    ErrorCode DoCommonInitialization(InitializationParameterOfDetector initializationParameterOfDetector);
+    void GetSSDParameter();
+    void GetResult(const std::vector<std::vector<float>> &classification,const std::vector<std::vector<float>> &regression,std::vector<ResultOfDetection> &resultsOfDetection);
+
+    std::vector<float> PermuteLayer(const std::vector<float> &data,int width,int height,int channels);
+    void PriorBoxLayer(int indexOfLayer,int* priorboxOutputData);
+    void SoftmaxLayer(int softMaxWidth[],int* softMaxInputData[], int* softMaxOutputData);
+    void DetectionOutputLayer(int* allLocPreds[], int* allPriorBoxes[],int* confScores, int* assistMemPool);
+
+    void ComputeSoftMax(int* src, int size, int* dst);
+    void QuickSort(int* src,int low, int high, QuickSortStack *stack,int maxNum);
+    void NonMaxSuppression( int* proposals, int anchorsNum,int NMSThresh,int maxRoiNum);
+    void Swap(int* src1, int* src2);
+    void ComputeOverlap(int xMin1, int yMin1, int xMax1, int yMax1, int xMin2,int yMin2, int xMax2, int yMax2,  int* areaSum, int* areaInter);
+    void CreateDetectionResults(std::vector<ResultOfDetection> &resultsOfDetection);
+
+private:
+    cv::FileStorage configurationFile;
+    InitializationParameterOfDetector initializationParameter;
+    FILE *logFile;
+    
+    migraphx::program net;
+    cv::Size inputSize;
+    string inputName;
+    migraphx::shape inputShape;
+
+    float scale;
+    cv::Scalar meanValue;
+    bool swapRB;
+    bool crop;
+    bool useInt8;
+    bool useFP16;
+
+    SSDParameter ssdParameter;
+
+};
+
+}
+
+#endif
+

Src/RetinaFace/SSDDefinition.h

+// SSD定义
+
+#ifndef __SSD_DEFINITION_H__
+#define __SSD_DEFINITION_H__
+
+#include <string>
+#include <vector>
+
+using namespace std;
+
+namespace migraphxSamples
+{
+
+#define SSD_MAX_PRIORBOX_LAYER_NUM      10 // 能够支持的最大检测层数量
+
+// SSD参数
+typedef struct _SSDParameter
+{
+    int numberOfPriorBoxLayer; // 检测层数量
+
+    // Model Parameters
+    int convHeight[SSD_MAX_PRIORBOX_LAYER_NUM*2];
+    int convWidth[SSD_MAX_PRIORBOX_LAYER_NUM*2];
+    int convChannel[SSD_MAX_PRIORBOX_LAYER_NUM*2];
+
+    // PriorBoxLayer Parameters
+    int priorBoxWidth[SSD_MAX_PRIORBOX_LAYER_NUM]; // 每个检测层priorbox的宽
+    int priorBoxHeight[SSD_MAX_PRIORBOX_LAYER_NUM];// 每个检测层priorbox的高
+    std::vector<std::vector<float>> priorBoxMinSize; // 每个检测层priorbox的minsize
+    std::vector<std::vector<float>> priorBoxMaxSize; // 每个检测层priorbox的maxsize
+    int minSizeNum[SSD_MAX_PRIORBOX_LAYER_NUM]; // 每个检测层priorbox的minsize数量
+    int maxSizeNum[SSD_MAX_PRIORBOX_LAYER_NUM]; // 每个检测层priorbox的maxsize数量
+    int srcImageHeight;// 原图大小
+    int srcImageWidth;
+    int inputAspectRatioNum[SSD_MAX_PRIORBOX_LAYER_NUM];// 每个检测层宽高比的数量 
+    std::vector<std::vector<float>> priorBoxAspectRatio;// 每个检测层的宽高比
+    float priorBoxStepWidth[SSD_MAX_PRIORBOX_LAYER_NUM];// 每个检测层步长的宽
+    float priorBoxStepHeight[SSD_MAX_PRIORBOX_LAYER_NUM];// 每个检测层步长的高
+    float offset;
+    int flip[SSD_MAX_PRIORBOX_LAYER_NUM];
+    int clip[SSD_MAX_PRIORBOX_LAYER_NUM];
+    int priorBoxVar[4];
+
+    // SoftmaxLayer Parameters
+    int softMaxInChn[SSD_MAX_PRIORBOX_LAYER_NUM];
+    int softMaxInHeight;
+    int concatNum;
+    int softMaxOutWidth;
+    int softMaxOutHeight;
+    int softMaxOutChn;
+
+    // DetectionOutLayer Parameters
+    int classNum;// 类别数(包含背景类)
+    int topK;
+    int keepTopK;
+    int NMSThresh;
+    int confThresh;
+    int detectInputChn[SSD_MAX_PRIORBOX_LAYER_NUM];
+    int convStride[SSD_MAX_PRIORBOX_LAYER_NUM];
+
+    // buffer
+    int *buffer;
+    int *classification[SSD_MAX_PRIORBOX_LAYER_NUM];// 分类数据
+    int *regression[SSD_MAX_PRIORBOX_LAYER_NUM];// 回归
+    int *priorboxOutputData;
+    int *softMaxOutputData;
+    int *getResultBuffer;
+    int *dstScore;
+    int *dstRoi;
+    int *classRoiNum;
+    _SSDParameter():srcImageHeight(0),
+                    srcImageWidth(0),
+                    offset(0.0),
+                    softMaxInHeight(0),
+                    concatNum(0),
+                    softMaxOutWidth(0),
+                    softMaxOutHeight(0),
+                    softMaxOutChn(0),
+                    buffer(NULL),
+                    priorboxOutputData(NULL),
+                    softMaxOutputData(NULL),
+                    getResultBuffer(NULL),
+                    dstScore(NULL),
+                    dstRoi(NULL),
+                    classRoiNum(NULL){}
+}SSDParameter;
+
+typedef struct _QuickSortStack
+{
+    int min;
+    int max;
+}QuickSortStack;
+
+}
+
+#endif
+

Src/Sample.cpp

+#include <Sample.h>
+#include <opencv2/dnn.hpp>
+#include <SimpleLog.h>
+#include <Filesystem.h>
+#include <DetectorRetinaFace.h>
+#include <fstream>
+
+
+using namespace std;
+using namespace cv;
+using namespace cv::dnn;
+using namespace migraphx;
+using namespace migraphxSamples;
+
+
+void Sample_DetectorRetinaFace()
+{
+    // 创建RetinaFace检测器
+    DetectorRetinaFace detector;
+    InitializationParameterOfDetector initParamOfDetectorRetinaFace;
+    initParamOfDetectorRetinaFace.parentPath = "";
+    initParamOfDetectorRetinaFace.configFilePath = CONFIG_FILE;
+    initParamOfDetectorRetinaFace.logName = "";
+    ErrorCode errorCode=detector.Initialize(initParamOfDetectorRetinaFace);
+    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/FaceDetect.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);
+        
+        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");
+}
\ No newline at end of file

Src/Sample.h

+// 示例程序
+
+#ifndef __SAMPLE_H__
+#define __SAMPLE_H__
+
+// RetinaFace sample
+void Sample_DetectorRetinaFace();
+
+#endif
\ No newline at end of file