【yolov5 ONNX】c++ 加载 导出的onnx模型

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
#include <fstream>

#include <opencv2/opencv.hpp>
//#include <torch/csrc/jit/frontend/tree.h>


std::vector<std::string> load_class_list()
{
	std::vector<std::string> class_list;
	std::ifstream ifs("weights/block.txt");
	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::readNetFromONNX("weights/best.onnx");//readNet   代码可用 版本有问题
	if (is_cuda)
	{
		std::cout << "Attempty to use CUDAn";
		result.setPreferableTarget(cv::dnn::DNN_TARGET_CUDA);
		result.setPreferableBackend(cv::dnn::DNN_BACKEND_CUDA);
		//result.setPreferableTarget(cv::dnn::DNN_TARGET_CUDA_FP16);
	}
	else
	{
		std::cout << "Running on CPUn";
		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 = 416.0;//640
const float INPUT_HEIGHT = 416.0;//640
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;
	std::vector<cv::String> blobnames = net.getUnconnectedOutLayersNames();
	std::cout << "before forwardn";
	net.forward(outputs, blobnames);//da4dnn::checkVersions CUDART version 11030 reported by cuDNN 8200 does not match with the version reported by CUDART 11010


	//outputs = net.forward();
	std::cout << "after forwardn";
	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 = 1;//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];// 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 filen";
		return -1;
	}

	bool is_cuda = argc > 1 && strcmp(argv[1], "cuda") == 0;
	is_cuda = true;//手动设置
	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 streamn";
			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 usern";
			break;
		}
	}

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

	return 0;
}