yolov5-6.1 opencv dnn onnx推理python,c++

yolov5 6.1 导出onnx

python export.py --include onnx

python

import cv2
import time
import sys
import numpy as np

def build_model(is_cuda):
    net = cv2.dnn.readNet("yolov5s.onnx")
    if is_cuda:
        print("Attempty to use CUDA")
        net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
        net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA_FP16)
    else:
        print("Running on CPU")
        net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
        net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
    return net

INPUT_WIDTH = 640
INPUT_HEIGHT = 640
SCORE_THRESHOLD = 0.2
NMS_THRESHOLD = 0.4
CONFIDENCE_THRESHOLD = 0.4

def detect(image, net):
    blob = cv2.dnn.blobFromImage(image, 1/255.0, (INPUT_WIDTH, INPUT_HEIGHT), swapRB=True, crop=False)
    net.setInput(blob)
    preds = net.forward()
    return preds

def load_capture():
    capture = cv2.VideoCapture("1.mp4")
    return capture

def load_classes():
    class_list = []
    with open("class.names", "r") as f:
        class_list = [cname.strip() for cname in f.readlines()]
    return class_list

class_list = load_classes()

def wrap_detection(input_image, output_data):
    class_ids = []
    confidences = []
    boxes = []

    rows = output_data.shape[0]

    image_width, image_height, _ = input_image.shape

    x_factor = image_width / INPUT_WIDTH
    y_factor =  image_height / INPUT_HEIGHT

    for r in range(rows):
        row = output_data[r]
        confidence = row[4]
        if confidence >= 0.4:

            classes_scores = row[5:]
            _, _, _, max_indx = cv2.minMaxLoc(classes_scores)
            class_id = max_indx[1]
            if (classes_scores[class_id] > .25):

                confidences.append(confidence)

                class_ids.append(class_id)

                x, y, w, h = row[0].item(), row[1].item(), row[2].item(), row[3].item() 
                left = int((x - 0.5 * w) * x_factor)
                top = int((y - 0.5 * h) * y_factor)
                width = int(w * x_factor)
                height = int(h * y_factor)
                box = np.array([left, top, width, height])
                boxes.append(box)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.25, 0.45) 

    result_class_ids = []
    result_confidences = []
    result_boxes = []

    for i in indexes:
        result_confidences.append(confidences[i])
        result_class_ids.append(class_ids[i])
        result_boxes.append(boxes[i])

    return result_class_ids, result_confidences, result_boxes

def format_yolov5(frame):

    row, col, _ = frame.shape
    _max = max(col, row)
    result = np.zeros((_max, _max, 3), np.uint8)
    result[0:row, 0:col] = frame
    return result


colors = [(255, 255, 0), (0, 255, 0), (0, 255, 255), (255, 0, 0)]

is_cuda = len(sys.argv) > 1 and sys.argv[1] == "cuda"

net = build_model(is_cuda)
capture = load_capture()

start = time.time()
frame_count = 0
total_frames = 0
fps = -1

while True:

    _, frame = capture.read()
    if frame is None:
        print("End of stream")
        break

    inputImage = format_yolov5(frame)
    outs = detect(inputImage, net)

    class_ids, confidences, boxes = wrap_detection(inputImage, outs[0])

    frame_count += 1
    total_frames += 1

    for (classid, confidence, box) in zip(class_ids, confidences, boxes):
         color = colors[int(classid) % len(colors)]
         cv2.rectangle(frame, box, color, 2)
         cv2.rectangle(frame, (box[0], box[1] - 20), (box[0] + box[2], box[1]), color, -1)
         cv2.putText(frame, class_list[classid], (box[0], box[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, .5, (0,0,0))

    if frame_count >= 30:
        end = time.time()
        fps =  frame_count / (end - start)
        frame_count = 0
        start = time.time()
    
    if fps > 0:
        fps_label = "FPS: %.2f" % fps
        cv2.putText(frame, fps_label, (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)

    cv2.imshow("output", frame)

    if cv2.waitKey(1) > -1:
        print("finished by user")
        break

print("Total frames: " + str(total_frames))

c++

#include 
#include 

std::vector<std::string> load_class_list()
{
    std::vector<std::string> class_list;
    std::ifstream ifs("class.names");
    std::string line;
    while (getline(ifs, line))
    {
        class_list.push_back(line);
    }
    return class_list;
}


void load_net(cv::dnn::Net &net, bool is_cuda)
{
    auto result = cv::dnn::readNet("yolov5s.onnx");
    if (is_cuda)
    {
        std::cout << "Attempty to use CUDA\n";
        result.setPreferableBackend(cv::dnn::DNN_BACKEND_CUDA);
        result.setPreferableTarget(cv::dnn::DNN_TARGET_CUDA_FP16);
    }
    else
    {
        std::cout << "Running on CPU\n";
        result.setPreferableBackend(cv::dnn::DNN_BACKEND_OPENCV);
        result.setPreferableTarget(cv::dnn::DNN_TARGET_CPU);
    }
    net = result;
}

const std::vector<cv::Scalar> colors = {cv::Scalar(255, 255, 0), cv::Scalar(0, 255, 0), cv::Scalar(0, 255, 255), cv::Scalar(255, 0, 0)};

const float INPUT_WIDTH = 640.0;
const float INPUT_HEIGHT = 640.0;
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;
};

cv::Mat format_yolov5(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;
}

void detect(cv::Mat &image, cv::dnn::Net &net, std::vector<Detection> &output, const std::vector<std::string> &className) {
    cv::Mat blob;

    auto input_image = format_yolov5(image);
    
    cv::dnn::blobFromImage(input_image, blob, 1./255., cv::Size(INPUT_WIDTH, INPUT_HEIGHT), cv::Scalar(), true, false);
    net.setInput(blob);
    std::vector<cv::Mat> outputs;
    net.forward(outputs, net.getUnconnectedOutLayersNames());

    float x_factor = input_image.cols / INPUT_WIDTH;
    float y_factor = input_image.rows / INPUT_HEIGHT;
    
    float *data = (float *)outputs[0].data;

    const int dimensions = 85;
    const int rows = 25200;
    
    std::vector<int> class_ids;
    std::vector<float> confidences;
    std::vector<cv::Rect> boxes;

    for (int i = 0; i < rows; ++i) {

        float confidence = data[4];
        if (confidence >= CONFIDENCE_THRESHOLD) {

            float * classes_scores = data + 5;
            cv::Mat scores(1, className.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 > SCORE_THRESHOLD) {

                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 += 85;

    }

    std::vector<int> nms_result;
    cv::dnn::NMSBoxes(boxes, confidences, SCORE_THRESHOLD, NMS_THRESHOLD, nms_result);
    for (int i = 0; i < nms_result.size(); i++) {
        int idx = nms_result[i];
        Detection result;
        result.class_id = class_ids[idx];
        result.confidence = confidences[idx];
        result.box = boxes[idx];
        output.push_back(result);
    }
}

int main(int argc, char **argv)
{

    std::vector<std::string> class_list = load_class_list();

    cv::Mat frame;
    cv::VideoCapture capture("1.mp4");
    if (!capture.isOpened())
    {
        std::cerr << "Error opening video file\n";
        return -1;
    }

    bool is_cuda = argc > 1 && strcmp(argv[1], "cuda") == 0;

    cv::dnn::Net net;
    load_net(net, is_cuda);

    auto start = std::chrono::high_resolution_clock::now();
    int frame_count = 0;
    float fps = -1;
    int total_frames = 0;

    while (true)
    {
        capture.read(frame);
        if (frame.empty())
        {
            std::cout << "End of stream\n";
            break;
        }

        std::vector<Detection> output;
        detect(frame, net, output, class_list);

        frame_count++;
        total_frames++;

        int detections = output.size();

        for (int i = 0; i < detections; ++i)
        {

            auto detection = output[i];
            auto box = detection.box;
            auto classId = detection.class_id;
            const auto color = colors[classId % colors.size()];
            cv::rectangle(frame, box, color, 3);

            cv::rectangle(frame, cv::Point(box.x, box.y - 20), cv::Point(box.x + box.width, box.y), color, cv::FILLED);
            cv::putText(frame, class_list[classId].c_str(), cv::Point(box.x, box.y - 5), cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(0, 0, 0));
        }

        if (frame_count >= 30)
        {

            auto end = std::chrono::high_resolution_clock::now();
            fps = frame_count * 1000.0 / std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count();

            frame_count = 0;
            start = std::chrono::high_resolution_clock::now();
        }

        if (fps > 0)
        {

            std::ostringstream fps_label;
            fps_label << std::fixed << std::setprecision(2);
            fps_label << "FPS: " << fps;
            std::string fps_label_str = fps_label.str();

            cv::putText(frame, fps_label_str.c_str(), cv::Point(10, 25), cv::FONT_HERSHEY_SIMPLEX, 1, cv::Scalar(0, 0, 255), 2);
        }

        cv::imshow("output", frame);

        if (cv::waitKey(1) != -1)
        {
            capture.release();
            std::cout << "finished by user\n";
            break;
        }
    }

    std::cout << "Total frames: " << total_frames << "\n";

    return 0;
}