OpenVion22.3.x以及Opencv DNN部署yolov5（C++）全过程含代码

部署Openvino在win平台上走了不少坑，这里将从第一步开始进行，避免以后遗忘。

第一步肯定是先把yolo5的工程跑通啦,基本上7.0运行一下会自动下载各种，非常方便，基本不存在复杂的配置过程。

跑通后需要pip一下export.py所需要的openvino包：

1.  openvino：这一般是OpenVINO的主要安装包，它包含了一系列的工具，库，和插件，用于优化，执行和部署各种深度学习模型。它可能包括但不限于Model Optimizer(模型优化器), nGraph API, Inference Engine(推理引擎)，以及不同硬件设备的插件等。                        openvino-dev：这个包通常包含用于开发者的头文件和库。为了开发自己的程序并与OpenVINO库接口，需要用到这些开发工具。​​​​​​                                                        ​​​​​​​        ​​​​​​​        ​​​​​​​openvino-telemetry：这个包与收集和发送运行时的数据或者日志有关，以便在系统运行过程中进行监视或者调试。版本不需要与前两版本一致也不影响。                                                                                                                                                                                                                                                                       

2.  具体配置export的部分：首先修改自己训练好的的pt模型路径，yaml路径根据自己需求选择导出的格式，这里选择openvino；然后运行一下等着就行啦，如果这里报错dll导入失败大概是版本不对应的问题。然后就得到xml和bin。XML文件：这个文件描述了模型的网络图结构。在这个文件中，你能找到每一层的信息，例如层名称，层类型，层参数，以及它们是如何连接起来的。BIN文件：这是一个二进制文件，包含了模型的权重和偏置。

3. 配置openvino和opencv部分VS+OpenCV+OpenVINO2022详细配置（更新） - 知乎 (zhihu.com)这部分照这个配置想应的vs环境就行。

4. 部署代码

   #include 
   #include 
   #include 
   
   
   using namespace std;
   
   
   const float SCORE_THRESHOLD = 0.2;
   const float NMS_THRESHOLD = 0.4;
   const float CONFIDENCE_THRESHOLD = 0.4;
   
   
   struct Detection
   {
       int class_id;
       float confidence;
       cv::Rect box;
   };
   
   
   struct Resize
   {
       cv::Mat resized_image;
       int dw;
       int dh;
   };
   
   
   Resize resize_and_pad(cv::Mat& img, cv::Size new_shape) {
       float width = img.cols;
       float height = img.rows;
       float r = float(new_shape.width / max(width, height));
       int new_unpadW = int(round(width * r));
       int new_unpadH = int(round(height * r));
       Resize resize;
       cv::resize(img, resize.resized_image, cv::Size(new_unpadW, new_unpadH), 0, 0, cv::INTER_AREA);
   
       resize.dw = new_shape.width - new_unpadW;
       resize.dh = new_shape.height - new_unpadH;
       cv::Scalar color = cv::Scalar(100, 100, 100);
       cv::copyMakeBorder(resize.resized_image, resize.resized_image, 0, resize.dh, 0, resize.dw, cv::BORDER_CONSTANT, color);
   
       return resize;
   }
   
   
   int main() {
   
       // Step 1. Initialize OpenVINO Runtime core
       ov::Core core;
       // Step 2. Read a model
       std::shared_ptr model = core.read_model("D://best.xml", "D://best.bin");
       //此处需要自行修改xml和bin的路径
   
       // Step 3. Read input image
       // 图像路径  
       cv::Mat img = cv::imread("D:/p.bmp");
       // resize image
       Resize res = resize_and_pad(img, cv::Size(640, 640));
   
   
       // Step 4. Inizialize Preprocessing for the model
       ov::preprocess::PrePostProcessor ppp = ov::preprocess::PrePostProcessor(model);
       // Specify input image format
       ppp.input().tensor().set_element_type(ov::element::u8).set_layout("NHWC").set_color_format(ov::preprocess::ColorFormat::BGR);
       // Specify preprocess pipeline to input image without resizing
       ppp.input().preprocess().convert_element_type(ov::element::f32).convert_color(ov::preprocess::ColorFormat::RGB).scale({ 255., 255., 255. });
       //  Specify model's input layout
       ppp.input().model().set_layout("NCHW");
       // Specify output results format
       ppp.output().tensor().set_element_type(ov::element::f32);
       // Embed above steps in the graph
       model = ppp.build();
       ov::CompiledModel compiled_model = core.compile_model(model, "CPU");
   
   
       // Step 5. Create tensor from image
       float* input_data = (float*)res.resized_image.data;
       ov::Tensor input_tensor = ov::Tensor(compiled_model.input().get_element_type(), compiled_model.input().get_shape(), input_data);
   
   
       // Step 6. Create an infer request for model inference 
       ov::InferRequest infer_request = compiled_model.create_infer_request();
       infer_request.set_input_tensor(input_tensor);
       //增加计时器统计推理时间
       double start = clock();
       infer_request.infer();
       double end = clock();
       double last = start - end;
       cout << "Detect Time" << last << "ms" << endl;
   
       //Step 7. Retrieve inference results 
       const ov::Tensor& output_tensor = infer_request.get_output_tensor();
       ov::Shape output_shape = output_tensor.get_shape();
       float* detections = output_tensor.data();
   
   
       // Step 8. Postprocessing including NMS  
       std::vector boxes;
       vector class_ids;
       vector confidences;
   
       for (int i = 0; i < output_shape[1]; i++) {
           float* detection = &detections[i * output_shape[2]];
   
           float confidence = detection[4];
           if (confidence >= CONFIDENCE_THRESHOLD) {
               float* classes_scores = &detection[5];
               cv::Mat scores(1, output_shape[2] - 5, CV_32FC1, classes_scores);
               cv::Point class_id;
               double max_class_score;
               cv::minMaxLoc(scores, 0, &max_class_score, 0, &class_id);
   
               if (max_class_score > SCORE_THRESHOLD) {
   
                   confidences.push_back(confidence);
   
                   class_ids.push_back(class_id.x);
   
                   float x = detection[0];
                   float y = detection[1];
                   float w = detection[2];
                   float h = detection[3];
   
                   float xmin = x - (w / 2);
                   float ymin = y - (h / 2);
   
                   boxes.push_back(cv::Rect(xmin, ymin, w, h));
               }
           }
       }
       std::vector nms_result;
       cv::dnn::NMSBoxes(boxes, confidences, SCORE_THRESHOLD, NMS_THRESHOLD, nms_result);
       std::vector output;
       for (int i = 0; i < nms_result.size(); i++)
       {
           Detection result;
           int idx = nms_result[i];
           result.class_id = class_ids[idx];
           result.confidence = confidences[idx];
           result.box = boxes[idx];
           output.push_back(result);
       }
   
   
       // Step 9. Print results and save Figure with detections
       for (int i = 0; i < output.size(); i++)
       {
           auto detection = output[i];
           auto box = detection.box;
           auto classId = detection.class_id;
           auto confidence = detection.confidence;
           float rx = (float)img.cols / (float)(res.resized_image.cols - res.dw);
           float ry = (float)img.rows / (float)(res.resized_image.rows - res.dh);
           box.x = rx * box.x;
           box.y = ry * box.y;
           box.width = rx * box.width;
           box.height = ry * box.height;
           cout << "Bbox" << i + 1 << ": Class: " << classId << " "
               << "Confidence: " << confidence << " Scaled coords: [ "
               << "cx: " << (float)(box.x + (box.width / 2)) / img.cols << ", "
               << "cy: " << (float)(box.y + (box.height / 2)) / img.rows << ", "
               << "w: " << (float)box.width / img.cols << ", "
               << "h: " << (float)box.height / img.rows << " ]" << endl;
           float xmax = box.x + box.width;
           float ymax = box.y + box.height;
           cv::rectangle(img, cv::Point(box.x, box.y), cv::Point(xmax, ymax), cv::Scalar(0, 255, 0), 3);
           cv::rectangle(img, cv::Point(box.x, box.y - 20), cv::Point(xmax, box.y), cv::Scalar(0, 255, 0), cv::FILLED);
           cv::putText(img, std::to_string(classId), cv::Point(box.x, box.y - 5), cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(0, 0, 0));
       }
       cv::imwrite("D:/pres.bmp", img);
       //显示具体结果
       cv::namedWindow("ImageWindow", cv::WINDOW_NORMAL);
       cv::resizeWindow("ImageWindow", 800, 600);
       cv::imshow("ImageWindow", img);
       
       cv::waitKey(0);
       cv::destroyAllWindows();
       return 0;
   }
   

   正常来说前面没问题这步就能直接跑啦，一般有问题的话可以选择从debug，release上选择哪个，配置是否有d考虑，其他各种崩溃都是版本原因引起，得从版本考虑，不行就重新装一次，版本问题确实麻烦，找起来不是非常方便，到这基本上就配置完成了。

5. 下面是opencvDNN的部署方式

   OpenCV DNN (Deep Neural Network) 是 OpenCV 库中的一个模块，旨在提供对深度神经网络的支持。它允许你加载、推理和使用预训练的深度学习模型，以进行对象检测、图像分类、姿态估计等计算机视觉任务。OpenCV DNN 模块支持各种深度学习框架训练的模型，使用 OpenCV DNN，你可以通过简单的 API 载入训练好的模型并输入图像进行推理。该模块提供了高性能的计算图执行引擎，允许在 CPU 或者支持 GPU 加速的硬件上实现实时图像处理和分析。总之，OpenCV DNN 为开发者提供了一种方便快捷的方式，利用深度学习模型进行图像处理和计算机视觉任务。

6. 此处贴上官方方法：Hexmagic/ONNX-yolov5: deploy yolov5 in c++ (github.com)因为原作者是在linux上配置我们是win，所以接下来，我们需要cmake一下cmakelist，然后就会得到一堆文件，新建过程，读取解决方案,当然，我们也可以直接复制他的源码自己建立一个工程也是可以的，不需要cmakelist，这里可以注意下打开后的话就会有四个项目，我们可以移除三个，剩个main即可，配置一下基本上opencv配置一下就行，然后就可以改改路径就可以run了。main.cpp：

   include 
   #include 
   #include 
   #include "loguru.hpp"
   #include "detector.h"
   using namespace cv;
   using namespace std;
   /* main */
   
   int main(int argc, char *argv[])
   {
       // 默认参数
       std::cout << "OpenCV version : " << CV_VERSION << std::endl;
       string model_path = "D://best.onnx";
       string img_path = "D://p.bmp";
       //string model_path = "3_best.onnx";
       //string img_path = "data/images/zidane.jpg";
       loguru::init(argc, argv);
       Config config = {0.25f, 0.45f, model_path, "E://yolo5//ONNX-yolov5-master//data//coco.names", Size(640, 640),false};
       LOG_F(INFO,"Start main process");
       Detector detector(config);
       LOG_F(INFO,"Load model done ..");
       Mat img = imread(img_path, IMREAD_COLOR);
       LOG_F(INFO,"Read image from %s", img_path.c_str());
       double start = clock();
       Detection detection = detector.detect(img);
       double end = clock();
       double last = start - end;
       cout << "Detect Time"<< last << "ms" << endl;
       LOG_F(INFO,"Detect process finished");
       Colors cl = Colors();
       detector.postProcess(img, detection,cl);
       LOG_F(INFO,"Post process done save image to assets/output.bmp");
       cv::imwrite("E:/yolo5/ONNX-yolov5-master/assets/p.bmp", img);
       std::cout << "detect Image And Save to assets/output.bmp" << endl;
       return 0;
   }

   到这基本上就结束了opencv和openvino部署的过程，大部分问题都可以从版本上寻找，因为部署代码多次测试是没有问题的。tks~