YOLO检测的三大步骤
- 载入cfg
- 载入weights
- 网络预测
C:\darknet-master\src\art.c
void demo_art(char *cfgfile, char *weightfile, int cam_index)
{
#ifdef OPENCV
network net = parse_network_cfg(cfgfile);//载入cfg
if(weightfile){//载入weights
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
cap_cv * cap;
cap = get_capture_webcam(cam_index);
char *window = "ArtJudgementBot9000!!!";
if(!cap) error("Couldn't connect to webcam.\n");
create_window_cv(window, 0, 512, 512);
int i;
int idx[] = {37, 401, 434};
int n = sizeof(idx)/sizeof(idx[0]);
while(1){
image in = get_image_from_stream_cpp(cap);
image in_s = resize_image(in, net.w, net.h);
show_image(in, window);
float *p = network_predict(net, in_s.data);//网络预测
printf("\033[2J");
printf("\033[1;1H");
float score = 0;
for(i = 0; i < n; ++i){
float s = p[idx[i]];
if (s > score) score = s;
}
score = score;
printf("I APPRECIATE THIS ARTWORK: %10.7f%%\n", score*100);
printf("[");
int upper = 30;
for(i = 0; i < upper; ++i){
printf("%c", ((i+.5) < score*upper) ? 219 : ' ');
}
printf("]\n");
free_image(in_s);
free_image(in);
wait_key_cv(1);
}
#endif
}
从图中代码可以看出步骤1,2仅进行的1次,步骤3在一直循环
基于src/yolo_v2_class.cpp的lib扩展的独立工程中这三个步骤的分布所在。
- 载入cfg
- 载入weights
位于构造函数中
class Detector {
std::shared_ptr<void> detector_gpu_ptr;
std::deque<std::vector<bbox_t>> prev_bbox_vec_deque;
public:
const int cur_gpu_id;
float nms = .4;
bool wait_stream;
LIB_API Detector(std::string cfg_filename, std::string weight_filename, int gpu_id = 0);
- 网络预测
在detect函数里
LIB_API std::vector<bbox_t> Detector::detect(image_t img, float thresh, bool use_mean)
{
detector_gpu_t &detector_gpu = *static_cast<detector_gpu_t *>(detector_gpu_ptr.get());
network &net = detector_gpu.net;
#ifdef GPU
int old_gpu_index;
cudaGetDevice(&old_gpu_index);
if(cur_gpu_id != old_gpu_index)
cudaSetDevice(net.gpu_index);
net.wait_stream = wait_stream; // 1 - wait CUDA-stream, 0 - not to wait
#endif
//std::cout << "net.gpu_index = " << net.gpu_index << std::endl;
image im;
im.c = img.c;
im.data = img.data;
im.h = img.h;
im.w = img.w;
image sized;
if (net.w == im.w && net.h == im.h) {
sized = make_image(im.w, im.h, im.c);
memcpy(sized.data, im.data, im.w*im.h*im.c * sizeof(float));
}
else
sized = resize_image(im, net.w, net.h);
layer l = net.layers[net.n - 1];
float *X = sized.data;
float *prediction = network_predict(net, X);