我们在Yolo官网上看到 训练,测试的 命令中都是
##实时:
./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights
##训练
./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74
examples
├── art.c
├── attention.c
├── captcha.c
├── cifar.c
├── classifier.c
├── coco.c
├── darknet.c
├── detector.c
├── detector.py
├── detector-scipy-opencv.py
├── dice.c
├── go.c
├── instance-segmenter.c
├── lsd.c
├── nightmare.c
├── regressor.c
├── rnn.c
├── rnn_vid.c
├── segmenter.c
├── super.c
├── swag.c
├── tag.c
├── voxel.c
├── writing.c
└── yolo.c
在darknet 主命令后面都接了一个detector ,那么在darknet 源码中, example 目录下 每一个C源码对应的时候 darknet 框架的 一个 项目; 探寻 yolo detection, 了解
//detector.c
void run_detector(int argc, char **argv)
{
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .5);
float hier_thresh = find_float_arg(argc, argv, "-hier", .5);
int cam_index = find_int_arg(argc, argv, "-c", 0);
int frame_skip = find_int_arg(argc, argv, "-s", 0);
int avg = find_int_arg(argc, argv, "-avg", 3);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
}
char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);
char *outfile = find_char_arg(argc, argv, "-out", 0);
int *gpus = 0;
int gpu = 0;
int ngpus = 0;
if(gpu_list){
printf("%s\n", gpu_list);
int len = strlen(gpu_list);
ngpus = 1;
int i;
for(i = 0; i < len; ++i){
if (gpu_list[i] == ',') ++ngpus;
}
gpus = calloc(ngpus, sizeof(int));
for(i = 0; i < ngpus; ++i){
gpus[i] = atoi(gpu_list);
gpu_list = strchr(gpu_list, ',')+1;
}
} else {
gpu = gpu_index;
gpus = &gpu;
ngpus = 1;
}
int clear = find_arg(argc, argv, "-clear");
int fullscreen = find_arg(argc, argv, "-fullscreen");
int width = find_int_arg(argc, argv, "-w", 0);
int height = find_int_arg(argc, argv, "-h", 0);
int fps = find_int_arg(argc, argv, "-fps", 0);
//int class = find_int_arg(argc, argv, "-class", 0);
char *datacfg = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
char *filename = (argc > 6) ? argv[6]: 0;
//不同的 命令 运行不同的函数
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, hier_thresh, outfile, fullscreen);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights, outfile);
else if(0==strcmp(argv[2], "valid2")) validate_detector_flip(datacfg, cfg, weights, outfile);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, avg, hier_thresh, width, height, fps, fullscreen);
}
//else if(0==strcmp(argv[2], "extract")) extract_detector(datacfg, cfg, weights, cam_index, filename, class, thresh, frame_skip);
//else if(0==strcmp(argv[2], "censor")) censor_detector(datacfg, cfg, weights, cam_index, filename, class, thresh, frame_skip);
}
重要部分在这:
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, hier_thresh, outfile, fullscreen);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights, outfile);
else if(0==strcmp(argv[2], "valid2")) validate_detector_flip(datacfg, cfg, weights, outfile);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, avg, hier_thresh, width, height, fps, fullscreen);
}
//else if(0==strcmp(argv[2], "extract")) extract_detector(datacfg, cfg, weights, cam_index, filename, class, thresh, frame_skip);
//else if(0==strcmp(argv[2], "censor")) censor_detector(datacfg, cfg, weights, cam_index, filename, class, thresh, frame_skip);
}
我们要训练 Yolo ,则去看detector.c 中的train_detector:
//detector.c
void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
{
list *options = read_data_cfg(datacfg);
char *train_images = option_find_str(options, "train", "data/train.list");
char *backup_directory = option_find_str(options, "backup", "/backup/");
/*srand函数是随机数发生器的初始化函数。
srand和rand()配合使用产生伪随机数序列。rand函数在产生随机数前，需要系统提供的生成伪随机数序列的
种子，rand根据这个种子的值产生一系列随机数。如果系统提供的种子没有变化，每次调用rand函数生成的伪
随机数序列都是一样的。*/
srand(time(0));
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
network **nets = calloc(ngpus, sizeof(network));
srand(time(0));
int seed = rand();
int i;
for(i = 0; i < ngpus; ++i){
srand(seed);
#ifdef GPU
cuda_set_device(gpus[i]);
#endif
nets[i] = load_network(cfgfile, weightfile, clear);
nets[i]->learning_rate *= ngpus;
}
srand(time(0));
network *net = nets[0];
//imgs是一次加载到内存的图像数量
int imgs = net->batch * net->subdivisions * ngpus;
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net->learning_rate, net->momentum, net->decay);
data train, buffer;
layer l = net->layers[net->n - 1];
int classes = l.classes;
//利用抖动(jittering)产生额外数据
float jitter = l.jitter;
list *plist = get_paths(train_images);
//int N = plist->size;
char **paths = (char **)list_to_array(plist);
load_args args = get_base_args(net);
args.coords = l.coords;
args.paths = paths;
args.n = imgs;
args.m = plist->size;
args.classes = classes;
args.jitter = jitter;
args.num_boxes = l.max_boxes;
args.d = &buffer;
args.type = DETECTION_DATA;
//args.type = INSTANCE_DATA;
args.threads = 64;
pthread_t load_thread = load_data(args);
double time;
int count = 0;
//while(i*imgs < N*120){
while(get_current_batch(net) < net->max_batches){
if(l.random && count++%10 == 0){
//随机改变 输入图片的size
printf("Resizing\n");
int dim = (rand() % 10 + 10) * 32;
if (get_current_batch(net)+200 > net->max_batches) dim = 608;
//int dim = (rand() % 4 + 16) * 32;
printf("%d\n", dim);
args.w = dim;
args.h = dim;
pthread_join(load_thread, 0);
train = buffer;
free_data(train);
//多线程读图片
load_thread = load_data(args);
#pragma omp parallel for
for(i = 0; i < ngpus; ++i){
//图片的输入不同,调整网络结构
resize_network(nets[i], dim, dim);
}
net = nets[0];
}
time=what_time_is_it_now();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data(args);
/*
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[10] + 1 + k*5);
if(!b.x) break;
printf("loaded: %f %f %f %f\n", b.x, b.y, b.w, b.h);
}
*/
/*
int zz;
for(zz = 0; zz < train.X.cols; ++zz){
image im = float_to_image(net->w, net->h, 3, train.X.vals[zz]);
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[zz] + k*5, 1);
printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);
draw_bbox(im, b, 1, 1,0,0);
}
show_image(im, "truth11");
cvWaitKey(0);
save_image(im, "truth11");
}
*/
printf("Loaded: %lf seconds\n", what_time_is_it_now()-time);
time=what_time_is_it_now();
float loss = 0;
#ifdef GPU
if(ngpus == 1){
loss = train_network(net, train);
} else {
loss = train_networks(nets, ngpus, train, 4);
}
#else
//计算LOSS
loss = train_network(net, train);
#endif
if (avg_loss < 0) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
i = get_current_batch(net);
printf("%ld: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), what_time_is_it_now()-time, i*imgs);
if(i%100==0){
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s.backup", backup_directory, base);
save_weights(net, buff);
}
if(i%10000==0 || (i < 1000 && i%100 == 0)){
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
}
free_data(train);
}
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
}
平均loss计算:
avg_loss = avg_loss.9 + loss.1;
网友评论