YOLO源码解析之yolo.c

yolo.c是YOLO模型源码的主文件，该文件包括以下函数：

train_yolo

void train_yolo(char *cfgfile, char *weightfile)
{
    char *train_images = "/data/voc/train.txt";
    char *backup_directory = "/home/pjreddie/backup/";
    srand(time(0));
    data_seed = time(0);
    char *base = basecfg(cfgfile);
    printf("%s\n", base);
    float avg_loss = -1;
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
    int imgs = net.batch*net.subdivisions;
    int i = *net.seen/imgs;
    data train, buffer;


    layer l = net.layers[net.n - 1];

    int side = l.side;
    int classes = l.classes;
    float jitter = l.jitter;

    list *plist = get_paths(train_images);
    //int N = plist->size;
    char **paths = (char **)list_to_array(plist);

    load_args args = {
  0};
    args.w = net.w;
    args.h = net.h;
    args.paths = paths;
    args.n = imgs;
    args.m = plist->size;
    args.classes = classes;
    args.jitter = jitter;
    args.num_boxes = side;
    args.d = &buffer;
    args.type = REGION_DATA;

    pthread_t load_thread = load_data_in_thread(args);
    clock_t time;
    //while(i*imgs < N*120){
   
    while(get_current_batch(net) < net.max_batches){
        i += 1;
        time=clock();
        pthread_join(load_thread, 0);
        train = buffer;
        load_thread = load_data_in_thread(args);

        printf("Loaded: %lf seconds\n", sec(clock()-time));

        time=clock();
        float loss = train_network(net, train);
        if (avg_loss < 0) avg_loss = loss;
        avg_loss = avg_loss*.9 + loss*.1;

        printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", i, loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
        if(i%1000==0 || (i < 1000 && i%100 == 0)){
            char buff[256];
            sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
            save_weights(net, buff);
        }
        free_data(train);
    }
    char buff[256];
    sprintf(buff, "%s/%s_final.weights", backup_directory, base);
    save_weights(net, buff);
}

convert_yolo_detections

void convert_yolo_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
{
    int i,j,n;
    //int per_cell = 5*num+classes;
    for (i = 0; i < side*side; ++i){
        int row = i / side;
        int col = i % side;
        for(n = 0; n < num; ++n){
            int index = i*num + n;
            int p_index = side*side*classes + i*num + n;
            float scale = predictions[p_index];
            int box_index = side*side*(classes + num) + (i*num + n)*4;
            boxes[index].x = (predictions[box_index + 0] &