mac安装opencv并在vscode中配置c++环境调试推理YOLOv8网络模型

OpenCV（Open Source Computer Vision Library）是一个开源的计算机视觉库，提供了丰富的图像处理和计算机视觉算法。它支持多平台（包括 Windows、Linux、macOS）和多种编程语言（如 C++、Python、Java），使其成为研究、开发和部署计算机视觉应用的重要工具之一。

步骤 1: 创建项目目录和必要的文件

1. 创建项目目录并进入：

   mkdir yolov8_project
   cd yolov8_project
   mkdir build
   

2. 创建 CMakeLists.txt 文件并添加内容：

   touch CMakeLists.txt
   

   内容如下：

   cmake_minimum_required(VERSION 3.10)
   project(yolov8)
   
   set(CMAKE_CXX_STANDARD 14)
   # Set OpenCV_DIR to the directory where OpenCVConfig.cmake is located
   set(OpenCV_DIR /usr/local/opt/opencv/lib/cmake/opencv4)
   
   # Find OpenCV package
   find_package(OpenCV REQUIRED)
   
   # Include OpenCV directories
   include_directories(${OpenCV_INCLUDE_DIRS})
   
   # Link OpenCV libraries
   add_executable(yolov8 yolov8.cpp)
   target_link_libraries(yolov8 ${OpenCV_LIBS})
   
   # Print OpenCV include directories and libraries
   message(STATUS "OpenCV include directories: ${OpenCV_INCLUDE_DIRS}")
   message(STATUS "OpenCV libraries: ${OpenCV_LIBS}")
   

3. 创建 yolov8.cpp 文件并添加您的代码：

   touch yolov8.cpp
   

   内容如下：

   #include <iostream>
   #include <opencv2/opencv.hpp>
   #include <opencv2/dnn/all_layers.hpp>
   #include <fstream>
   
   using namespace std;
   using namespace cv;
   
   struct DCSP_RESULT {
        
       int classId;
       float confidence;
       cv::Rect box;
   };
   
   void process(cv::Mat& blob, cv::dnn::Net& net, std::vector<cv::Mat>& outputs) {
        
       net.setInput(blob);
       net.forward(outputs, net.getUnconnectedOutLayersNames());
   }
   
   void pre_process(cv::Mat& image, cv::Mat& blob) {
        
       cv::dnn::blobFromImage(image, blob, 1. / 255., cv::Size(640, 640), cv::Scalar(0, 0, 0), true, false);
   }
   
   void saveTensor(const std::string& filename, const cv::Mat& tensor) {
        
       std::ofstream file(filename, std::ios::binary);
       if (file.is_open()) {
        
           file.write(reinterpret_cast<const char*>(tensor.data), tensor.total() * tensor.elemSize());
           file.close();
       }
   }
   
   void post_process(cv::Mat& image, const std::vector<cv::Mat>& outs, float confThreshold,</