yolov3测试集recall

validate_detector   example/detector.c

void validate_detector(char *datacfg, char *cfgfile, char *weightfile, char *outfile)
{
    int j;
    list *options = read_data_cfg(datacfg);
    char *valid_images = option_find_str(options, "valid", "data/train.list");
    char *name_list = option_find_str(options, "names", "data/names.list");
    char *prefix = option_find_str(options, "results", "results");
    char **names = get_labels(name_list);
    char *mapf = option_find_str(options, "map", 0);
    int *map = 0;
    if (mapf) map = read_map(mapf);

    network *net = load_network(cfgfile, weightfile, 0);
    set_batch_network(net, 1);
    fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net->learning_rate, net->momentum, net->decay);
    srand(time(0));

    list *plist = get_paths(valid_images);
    char **paths = (char **)list_to_array(plist);

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

    char buff[1024];
    char *type = option_find_str(options, "eval", "voc");
    FILE *fp = 0;
    FILE **fps = 0;
    int coco = 0;
    int imagenet = 0;
    if(0==strcmp(type, "coco")){
        if(!outfile) outfile = "coco_results";
        snprintf(buff, 1024, "%s/%s.json", prefix, outfile);
        fp = fopen(buff, "w");
        fprintf(fp, "[\n");
        coco = 1;
    } else if(0==strcmp(type, "imagenet")){
        if(!outfile) outfile = "imagenet-detection";
        snprintf(buff, 1024, "%s/%s.txt", prefix, outfile);
        fp = fopen(buff, "w");
        imagenet = 1;
        classes = 200;
    } else {
        if(!outfile) outfile = "comp4_det_test_";
        fps = calloc(classes, sizeof(FILE *));
        for(j = 0; j < classes; ++j){
            snprintf(buff, 1024, "%s/%s%s.txt", prefix, outfile, names[j]);
            fps[j] = fopen(buff, "w");
        }
    }


    int m = plist->size;
    int i=0;
    int t;

    float thresh = .1;
    float nms = .45;

    int nthreads = 4;
    image *val = calloc(nthreads, sizeof(image));
    image *val_resized = calloc(nthreads, sizeof(image));
    image *buf = calloc(nthreads, sizeof(image));
    image *buf_resized = calloc(nthreads, sizeof(image));
    pthread_t *thr = calloc(nthreads, sizeof(pthread_t));

    load_args args = {0};
    args.w = net->w;
    args.h = net->h;
    //args.type = IMAGE_DATA;
    args.type = LETTERBOX_DATA;

    for(t = 0; t < nthreads; ++t){
        args.path = paths[i+t];
        args.im = &buf[t];
        args.resized = &buf_resized[t];
        thr[t] = load_data_in_thread(args);
    }
    double start = what_time_is_it_now();
    for(i = nthreads; i < m+nthreads; i += nthreads){
        fprintf(stderr, "%d\n", i);
        for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
            pthread_join(thr[t], 0);
            val[t] = buf[t];
            val_resized[t] = buf_resized[t];
        }
        for(t = 0; t < nthreads && i+t < m; ++t){
            args.path = paths[i+t];
            args.im = &buf[t];
            args.resized = &buf_resized[t];
            thr[t] = load_data_in_thread(args);
        }
        for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
            char *path = paths[i+t-nthreads];
            char *id = basecfg(path);
            float *X = val_resized[t].data;
            network_predict(net, X);
            int w = val[t].w;
            int h = val[t].h;
            int nboxes = 0;
            detection *dets = get_network_boxes(net, w, h, thresh, .5, map, 0, &nboxes);
            if (nms) do_nms_sort(dets, nboxes, classes, nms);
            if (coco){
                print_cocos(fp, path, dets, nboxes, classes, w, h);
            } else if (imagenet){
                print_imagenet_detections(fp, i+t-nthreads+1, dets, nboxes, classes, w, h);
            } else {
                print_detector_detections(fps, id, dets, nboxes, classes, w, h);
            }
            free_detections(dets, nboxes);
            free(id);
            free_image(val[t]);
            free_image(val_resized[t]);
        }
    }
    for(j = 0; j < classes; ++j){
        if(fps) fclose(fps[j]);
    }
    if(coco){
        fseek(fp, -2, SEEK_CUR); 
        fprintf(fp, "\n]\n");
        fclose(fp);
    }
    fprintf(stderr, "Total Detection Time: %f Seconds\n", what_time_is_it_now() - start);
}

get_network_boxes  src/network.c

detection *get_network_boxes(network *net, int w, int h, float thresh, float hier, int *map, int relative, int *num)
{
    detection *dets = make_network_boxes(net, thresh, num);
    fill_network_boxes(net, w, h, thresh, hier, map, relative, dets);
    return dets;
}

fill_network_boxes

src/network.c
void fill_network_boxes(network *net, int w, int h, float thresh, float hier, int *map, int relative, detection *dets)
{
    int j;
    for(j = 0; j < net->n; ++j){
        layer l = net->layers[j];
        if(l.type == YOLO){
            int count = get_yolo_detections(l, w, h, net->w, net->h, thresh, map, relative, dets);
            dets += count;
        }
        if(l.type == REGION){
            get_region_detections(l, w, h, net->w, net->h, thresh, map, hier, relative, dets);
            dets += l.w*l.h*l.n;
        }
        if(l.type == DETECTION){
            get_detection_detections(l, w, h, thresh, dets);
            dets += l.w*l.h*l.n;
        }
    }
}

src/yolo_layer.c
int get_yolo_detections(layer l, int w, int h, int netw, int neth, float thresh, int *map, int relative, detection *dets)
{
    int i,j,n;
    float *predictions = l.output;
    if (l.batch == 2) avg_flipped_yolo(l);
    int count = 0;
    for (i = 0; i < l.w*l.h; ++i){
        int row = i / l.w;
        int col = i % l.w;
        for(n = 0; n < l.n; ++n){
            int obj_index  = entry_index(l, 0, n*l.w*l.h + i, 4);
            float objectness = predictions[obj_index];
            if(objectness <= thresh) continue;
            int box_index  = entry_index(l, 0, n*l.w*l.h + i, 0);
            dets[count].bbox = get_yolo_box(predictions, l.biases, l.mask[n], box_index, col, row, l.w, l.h, netw, neth, l.w*l.h);
            dets[count].objectness = objectness;
            dets[count].classes = l.classes;
            for(j = 0; j < l.classes; ++j){
                int class_index = entry_index(l, 0, n*l.w*l.h + i, 4 + 1 + j);
                float prob = objectness*predictions[class_index];
                dets[count].prob[j] = (prob > thresh) ? prob : 0;
            }
            ++count;
        }
    }
    correct_yolo_boxes(dets, count, w, h, netw, neth, relative);
    return count;
}

src/yolo_layer.c

src/yolo_layer.c
void correct_yolo_boxes(detection *dets, int n, int w, int h, int netw, int neth, int relative)
{
    int i;
    int new_w=0;
    int new_h=0;
    if (((float)netw/w) < ((float)neth/h)) {
        new_w = netw;
        new_h = (h * netw)/w;
    } else {
        new_h = neth;
        new_w = (w * neth)/h;
    }
    for (i = 0; i < n; ++i){
        box b = dets[i].bbox;
        b.x =  (b.x - (netw - new_w)/2./netw) / ((float)new_w/netw); 
        b.y =  (b.y - (neth - new_h)/2./neth) / ((float)new_h/neth); 
        b.w *= (float)netw/new_w;
        b.h *= (float)neth/new_h;
        if(!relative){
            b.x *= w;
            b.w *= w;
            b.y *= h;
            b.h *= h;
        }
        dets[i].bbox = b;
    }
}

relative  = 0 代表输出为绝对尺寸

relative  = 1 代表输出为相对尺寸