retinaface.h
2.26 KB
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
#ifndef RETINAFACE_H
#define RETINAFACE_H
#include<opencv2/opencv.hpp>
using namespace std;
using namespace cv;
struct Bbox{
float xmin;
float ymin;
float xmax;
float ymax;
float score;
float x1;
float y1;
float x2;
float y2;
float x3;
float y3;
float x4;
float y4;
float x5;
float y5;
};
class RetinaFace{
private:
bool use_gpu=true;
vector<float> input_size={640,640};
vector<float> variances={0.1,0.2};
vector<float> mean_data={104,117,128};
float confidence_threshold = 0.8;
float keep_top_k = 100;
float vis_threshold = 0.2;
float nms_threshold = 0.4;
float resize_scale = 1.0;
bool is_bbox_process=true;
cv::dnn::Net net;
vector<vector<float>> anchors;
private:
// 生成anchors
vector<vector<float>> priorBox(vector<float> image_size);
// 解析bounding box landmarks 包含置信度
vector<Bbox> decode(Mat loc,Mat score,Mat pre,vector<vector<float>> priors,vector<float> variances);
// 解析landmarks
// vector<vector<float>> decode_landm(vector<vector<float>> pre,vector<vector<float>> priors,vector<float> variances);
//NMS
void nms_cpu(std::vector<Bbox> &bboxes, float threshold);
// Mat转vector
vector<vector<float>> mat2vector(Mat mat);
// 根据阈值筛选
vector<Bbox> select_score(vector<Bbox> bboxes,float threshold,float w_r,float h_r);
// vector转Bbox
// vector<Bbox> vec2Bbox(vector<vector<float>> bbox,float w_r,float h_r);
// 数据后处理
vector<Bbox> bbox_process(bool is_bbox_process,vector<Bbox> bboxes,float frame_w,float frame_h);
public:
RetinaFace(){};
RetinaFace(string model_path){
net = cv::dnn::readNetFromONNX(model_path);
if(use_gpu){
net.setPreferableBackend(cv::dnn::DNN_BACKEND_CUDA);
net.setPreferableTarget(cv::dnn::DNN_TARGET_CUDA);
}
anchors=priorBox(input_size);
}
// 推理
vector<Bbox> detect(string image_path);
vector<Bbox> detect_image(Mat image);
};
#endif