1、模型转换
1.在根目录下新建ptToOnnx.py文件,内容如下,运行后会在模型文件同目录下生成.onnx文件。
from ultralytics import YOLO
# Load a model
model = YOLO('runs/detect/train11/weights/best.pt') # load an official model
# Export the model
model.export(format='onnx', imgsz=[480, 640], opset=12) # 导出一定不要修改这里参数
运行后如下所示
2、安装opencv4.8.1
1.到官网下载opencv4.8.1版本,在此之前使用opencv4.6.0报错读取不了onnx模型。
2.安装后修改系统环境变量,并在VS2022中配置opencv4.8.1的环境
3.以下是main.cpp内容
#include <iostream>
#include <vector>
#include <opencv2/opencv.hpp>
#include "inference.h"
using namespace std;
using namespace cv;
int main(int argc, char** argv)
{
bool runOnGPU = false;
/*1. 设置你的onnx模型
Note that in this example the classes are hard-coded and 'classes.txt' is a place holder.*/
Inference inf("./weight/best.onnx", cv::Size(640, 480), "classes.txt", runOnGPU); // classes.txt 可以缺失
// 2. 设置你的输入图片
std::vector<std::string> imageNames;
imageNames.push_back("./image/testBatch.jpg");
//imageNames.push_back("zidane.jpg");
for (int i = 0; i < imageNames.size(); ++i)
{
cv::Mat frame = cv::imread(imageNames[i]);
// Inference starts here...
std::vector<Detection> output = inf.runInference(frame);
int detections = output.size();
std::cout << "Number of detections:" << detections << std::endl;
// feiyull
// 这里需要resize下,否则结果不对
//cv::resize(frame, frame, cv::Size(480, 640));
for (int i = 0; i < detections; ++i)
{
Detection detection = output[i];
cv::Rect box = detection.box;
cv::Scalar color = detection.color;
// Detection box
cv::rectangle(frame, box, color, 2);
// Detection box text
std::string classString = detection.className + ' ' + std::to_string(detection.confidence).substr(0, 4);
cv::Size textSize = cv::getTextSize(classString, cv::FONT_HERSHEY_DUPLEX, 1, 2, 0);
cv::Rect textBox(box.x, box.y - 40, textSize.width + 10, textSize.height + 20);
cv::rectangle(frame, textBox, color, cv::FILLED);
cv::putText(frame, classString, cv::Point(box.x + 5, box.y - 10), cv::FONT_HERSHEY_DUPLEX, 1, cv::Scalar(0, 0, 0), 2, 0);
}
cv::imshow("Inference", frame);
cv::waitKey(0);
cv::destroyAllWindows();
}
}
inference.h
classes中要根据自己的类别进行修改
#pragma once
#ifndef INFERENCE_H
#define INFERENCE_H
// Cpp native
#include <fstream>
#include <vector>
#include <string>
#include <random>
// OpenCV / DNN / Inference
#include <opencv2/imgproc.hpp>
#include <opencv2/opencv.hpp>
#include <opencv2/dnn.hpp>
struct Detection
{
int class_id{ 0 };
std::string className{};
float confidence{ 0.0 };
cv::Scalar color{};
cv::Rect box{};
};
class Inference
{
public:
Inference(const std::string& onnxModelPath, const cv::Size& modelInputShape = { 640, 640 }, const std::string& classesTxtFile = "", const bool& runWithCuda = true);
std::vector<Detection> runInference(const cv::Mat& input);
private:
void loadClassesFromFile();
void loadOnnxNetwork();
cv::Mat formatToSquare(const cv::Mat& source);
std::string modelPath{};
std::string classesPath{};
bool cudaEnabled{};
std::vector<std::string> classes{ "batchnum" };
cv::Size2f modelShape{};
float modelConfidenceThreshold{ 0.25 };
float modelScoreThreshold{ 0.45 };
float modelNMSThreshold{ 0.50 };
bool letterBoxForSquare = true;
cv::dnn::Net net;
};
#endif // INFERENCE_H
inference.cpp
#include "inference.h"
Inference::Inference(const std::string& onnxModelPath, const cv::Size& modelInputShape, const std::string& classesTxtFile, const bool& runWithCuda)
{
modelPath = onnxModelPath;
modelShape = modelInputShape;
classesPath = classesTxtFile;
cudaEnabled = runWithCuda;
loadOnnxNetwork();
// loadClassesFromFile(); The classes are hard-coded for this example
}
std::vector<Detection> Inference::runInference(const cv::Mat& input)
{
cv::Mat modelInput = input;
if (letterBoxForSquare && modelShape.width == modelShape.height)
modelInput = formatToSquare(modelInput);
cv::Mat blob;
cv::dnn::blobFromImage(modelInput, blob, 1.0 / 255.0, modelShape, cv::Scalar(), true, false);
net.setInput(blob);
std::vector<cv::Mat> outputs;
net.forward(outputs, net.getUnconnectedOutLayersNames());
int rows = outputs[0].size[1];
int dimensions = outputs[0].size[2];
bool yolov8 = false;
// yolov5 has an output of shape (batchSize, 25200, 85) (Num classes + box[x,y,w,h] + confidence[c])
// yolov8 has an output of shape (batchSize, 84, 8400) (Num classes + box[x,y,w,h])
if (dimensions > rows) // Check if the shape[2] is more than shape[1] (yolov8)
{
yolov8 = true;
rows = outputs[0].size[2];
dimensions = outputs[0].size[1];
outputs[0] = outputs[0].reshape(1, dimensions);
cv::transpose(outputs[0], outputs[0]);
}
float* data = (float*)outputs[0].data;
float x_factor = modelInput.cols / modelShape.width;
float y_factor = modelInput.rows / modelShape.height;
std::vector<int> class_ids;
std::vector<float> confidences;
std::vector<cv::Rect> boxes;
for (int i = 0; i < rows; ++i)
{
if (yolov8)
{
float* classes_scores = data + 4;
cv::Mat scores(1, classes.size(), CV_32FC1, classes_scores);
cv::Point class_id;
double maxClassScore;
minMaxLoc(scores, 0, &maxClassScore, 0, &class_id);
if (maxClassScore > modelScoreThreshold)
{
confidences.push_back(maxClassScore);
class_ids.push_back(class_id.x);
float x = data[0];
float y = data[1];
float w = data[2];
float h = data[3];
int left = int((x - 0.5 * w) * x_factor);
int top = int((y - 0.5 * h) * y_factor);
int width = int(w * x_factor);
int height = int(h * y_factor);
boxes.push_back(cv::Rect(left, top, width, height));
}
}
else // yolov5
{
float confidence = data[4];
if (confidence >= modelConfidenceThreshold)
{
float* classes_scores = data + 5;
cv::Mat scores(1, classes.size(), CV_32FC1, classes_scores);
cv::Point class_id;
double max_class_score;
minMaxLoc(scores, 0, &max_class_score, 0, &class_id);
if (max_class_score > modelScoreThreshold)
{
confidences.push_back(confidence);
class_ids.push_back(class_id.x);
float x = data[0];
float y = data[1];
float w = data[2];
float h = data[3];
int left = int((x - 0.5 * w) * x_factor);
int top = int((y - 0.5 * h) * y_factor);
int width = int(w * x_factor);
int height = int(h * y_factor);
boxes.push_back(cv::Rect(left, top, width, height));
}
}
}
data += dimensions;
}
std::vector<int> nms_result;
cv::dnn::NMSBoxes(boxes, confidences, modelScoreThreshold, modelNMSThreshold, nms_result);
std::vector<Detection> detections{};
for (unsigned long i = 0; i < nms_result.size(); ++i)
{
int idx = nms_result[i];
Detection result;
result.class_id = class_ids[idx];
result.confidence = confidences[idx];
std::random_device rd;
std::mt19937 gen(rd());
std::uniform_int_distribution<int> dis(100, 255);
result.color = cv::Scalar(dis(gen),
dis(gen),
dis(gen));
result.className = classes[result.class_id];
result.box = boxes[idx];
detections.push_back(result);
}
return detections;
}
void Inference::loadClassesFromFile()
{
std::ifstream inputFile(classesPath);
if (inputFile.is_open())
{
std::string classLine;
while (std::getline(inputFile, classLine))
classes.push_back(classLine);
inputFile.close();
}
}
void Inference::loadOnnxNetwork()
{
net = cv::dnn::readNetFromONNX(modelPath);
if (cudaEnabled)
{
std::cout << "\nRunning on CUDA" << std::endl;
net.setPreferableBackend(cv::dnn::DNN_BACKEND_CUDA);
net.setPreferableTarget(cv::dnn::DNN_TARGET_CUDA);
}
else
{
std::cout << "\nRunning on CPU" << std::endl;
net.setPreferableBackend(cv::dnn::DNN_BACKEND_OPENCV);
net.setPreferableTarget(cv::dnn::DNN_TARGET_CPU);
}
}
cv::Mat Inference::formatToSquare(const cv::Mat& source)
{
int col = source.cols;
int row = source.rows;
int _max = MAX(col, row);
cv::Mat result = cv::Mat::zeros(_max, _max, CV_8UC3);
source.copyTo(result(cv::Rect(0, 0, col, row)));
return result;
}
4.运行该工程后如下所示