void Darknet::yoloImage(const QString &filename, float thresh) { const Mat ori = OpenCV::loadImage(getAbs(filename), -1); Mat img; cv::resize(ori, img, cv::Size(priv->net.w, priv->net.h)); image im = toDarkImage(img); //image im = load_image_color((char *)qPrintable(getAbs(filename)), 0, 0); //image sized = resize_image(im, priv->net.w, priv->net.h); //float *X = sized.data; float *X = im.data; float *predictions = network_predict(priv->net, X); float nms=.5; const detection_layer l = priv->l; convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, priv->probs, priv->boxes, 0); if (nms) do_nms_sort(priv->boxes, priv->probs, l.side*l.side*l.n, l.classes, nms); draw_detections(im, l.side*l.side*l.n, thresh, priv->boxes, priv->probs, voc_names, 0, 20); show_image(im, "predictions"); save_image(im, "predictions"); //show_image(sized, "resized"); free_image(im); //free_image(sized); }
void test_yolo(char *cfgfile, char *weightfile, char *filename, float thresh) { network net = parse_network_cfg(cfgfile); if(weightfile){ load_weights(&net, weightfile); } detection_layer l = net.layers[net.n-1]; set_batch_network(&net, 1); srand(2222222); clock_t time; char buff[256]; char *input = buff; int j; float nms=.5; box *boxes = calloc(l.side*l.side*l.n, sizeof(box)); float **probs = calloc(l.side*l.side*l.n, sizeof(float *)); for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *)); while(1){ if(filename){ strncpy(input, filename, 256); } else { printf("Enter Image Path: "); fflush(stdout); input = fgets(input, 256, stdin); if(!input) return; strtok(input, "\n"); } image im = load_image_color(input,0,0); image sized = resize_image(im, net.w, net.h); float *X = sized.data; time=clock(); float *predictions = network_predict(net, X); printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time)); convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0); if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms); //draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20); draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, 0, 20); show_image(im, "predictions"); save_image(im, "predictions"); show_image(sized, "resized"); free_image(im); free_image(sized); #ifdef OPENCV cvWaitKey(0); cvDestroyAllWindows(); #endif if (filename) break; } }
void *detect_in_thread(void *ptr) { float nms = .4; layer_t l = net.layers[net.n-1]; float *X = det_s.data; float *predictions = network_predict(net, X); free_image(det_s); convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, demo_thresh, probs, boxes, 0); if (nms > 0) do_nms(boxes, probs, l.side*l.side*l.n, l.classes, nms); printf("\033[2J"); printf("\033[1;1H"); printf("\nFPS:%.0f\n",fps); printf("Objects:\n\n"); draw_detections(det, l.side*l.side*l.n, demo_thresh, boxes, probs, voc_names, voc_labels, 20); return 0; }
Mat Darknet::predict(const Mat &ori, float thresh) { Mat img; cv::resize(ori, img, cv::Size(priv->net.w, priv->net.h)); image im = toDarkImage(img); float nms = 0.5; /* NOTE: network_predict doesn't allocate any data */ float *predictions = network_predict(priv->net, im.data); const detection_layer l = priv->l; convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, priv->probs, priv->boxes, 0); if (nms) do_nms_sort(priv->boxes, priv->probs, l.side*l.side*l.n, l.classes, nms); draw_detections(im, l.side*l.side*l.n, thresh, priv->boxes, priv->probs, voc_names, 0, 20); Mat ret = toCVImage(im); free_image(im); return ret; }
void Darknet::predict(const QString &filename, float thresh) { const Mat ori = OpenCV::loadImage(getAbs(filename), -1); Mat img; cv::resize(ori, img, cv::Size(priv->net.w, priv->net.h)); image im = toDarkImage(img); float nms = 0.5; /* NOTE: network_predict doesn't allocate any data */ float *predictions = network_predict(priv->net, im.data); const detection_layer l = priv->l; convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, priv->probs, priv->boxes, 0); if (nms) do_nms_sort(priv->boxes, priv->probs, l.side*l.side*l.n, l.classes, nms); draw_detections(im, l.side*l.side*l.n, thresh, priv->boxes, priv->probs, voc_names, 0, 20); save_image(im, (char *)qPrintable(getAbs(QString(filename).replace(".jpg", "_pred.jpg")))); //ffDebug() << priv->net.n << priv->net.outputs << priv->l.classes; }
static void yolo_image2(const char *cfg, const char *weights, const char *filename, float thresh) { int i; for (i = 0; i < 20; ++i){ char buff[256]; sprintf(buff, "/home/amenmd/myfs/source-codes/oss/darknet/data/labels/%s.png", voc_names[i]); voc_labels[i] = load_image_color(buff, 0, 0); } network net = parse_network_cfg((char *)cfg); load_weights(&net, (char *)weights); detection_layer l = net.layers[net.n-1]; set_batch_network(&net, 1); int j; float nms=.5; box *boxes = (box *)calloc(l.side*l.side*l.n, sizeof(box)); float **probs = (float **)calloc(l.side*l.side*l.n, sizeof(float *)); for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = (float *)calloc(l.classes, sizeof(float *)); image im = load_image_color((char *)filename, 0, 0); image sized = resize_image(im, net.w, net.h); float *X = sized.data; float *predictions = network_predict(net, X); convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0); if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms); //draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20); draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, 0, 20); show_image(im, "predictions"); save_image(im, "predictions"); show_image(sized, "resized"); free_image(im); free_image(sized); }
void validate_yolo_classify(char *datacfg, char *cfgfile, char *weightfile) { list *options = read_data_cfg(datacfg); //char *train_list = option_find_str(options, "train", "data/train_list.txt"); //char *test_list = option_find_str(options, "test", "data/test_list.txt"); char *valid_list = option_find_str(options, "valid", "data/valid_list.txt"); //char *backup_directory = option_find_str(options, "backup", "/backup/"); //char *label_list = option_find_str(options, "labels", "data/labels_list.txt"); //int classes = option_find_int(options, "classes", 2); //char **labels = get_labels(label_list); network net = parse_network_cfg(cfgfile); if(weightfile){ load_weights(&net, weightfile); } 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)); char *base = "results/comp4_det_test_"; //list *plist = get_paths("data/voc.2007.test"); list *plist = get_paths(valid_list); char **paths = (char **)list_to_array(plist); layer l = net.layers[net.n-1]; int classes = l.classes; int square = l.sqrt; int side = l.side; int j, k; FILE **fps = calloc(classes, sizeof(FILE *)); for(j = 0; j < classes; ++j){ char buff[1024]; snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]); fps[j] = fopen(buff, "w"); } box *boxes = calloc(side*side*l.n, sizeof(box)); float **probs = calloc(side*side*l.n, sizeof(float *)); for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *)); int m = plist->size; int i=0; //float thresh = .001; float thresh = .2; float iou_thresh = .5; //float nms = 0; float nms = 0.5; int total = 0; int correct = 0; int class_correct = 0; int proposals = 0; float avg_iou = 0; for(i = 0; i < m; ++i){ char *path = paths[i]; image orig = load_image_color(path, 0, 0); image sized = resize_image(orig, net.w, net.h); char *id = basecfg(path); float *predictions = network_predict(net, sized.data); convert_yolo_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 0); //if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms); if (nms) do_nms(boxes, probs, side*side*l.n, classes, nms); char *labelpath = find_replace(path, "images", "labels"); labelpath = find_replace(labelpath, "JPEGImages", "labels"); labelpath = find_replace(labelpath, ".jpg", ".txt"); labelpath = find_replace(labelpath, ".JPEG", ".txt"); labelpath = find_replace(labelpath, ".bmp", ".txt"); labelpath = find_replace(labelpath, ".dib", ".txt"); labelpath = find_replace(labelpath, ".jpe", ".txt"); labelpath = find_replace(labelpath, ".jp2", ".txt"); labelpath = find_replace(labelpath, ".png", ".txt"); labelpath = find_replace(labelpath, ".pbm", ".txt"); labelpath = find_replace(labelpath, ".pgm", ".txt"); labelpath = find_replace(labelpath, ".ppm", ".txt"); labelpath = find_replace(labelpath, ".sr", ".txt"); labelpath = find_replace(labelpath, ".ras", ".txt"); labelpath = find_replace(labelpath, ".tiff", ".txt"); labelpath = find_replace(labelpath, ".tif", ".txt"); int num_labels = 0; box_label *truth = read_boxes(labelpath, &num_labels); for(k = 0; k < side*side*l.n; ++k){ int class = max_index(probs[k], classes); float prob = probs[k][class]; //fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class); if(prob > thresh){ ++proposals; } } for (j = 0; j < num_labels; ++j) { ++total; box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h}; float best_iou = 0; int pre_class = -1; for(k = 0; k < side*side*l.n; ++k){ float iou = box_iou(boxes[k], t); int class = max_index(probs[k], classes); float prob = probs[k][class]; //fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class); if(prob > thresh && iou > best_iou){ best_iou = iou; pre_class = class; } } avg_iou += best_iou; if(best_iou > iou_thresh){ ++correct; } if(pre_class == truth[j].id){ ++class_correct; } //fprintf(stderr, "true_class=%d\tpre_class=%d\n", truth[j].id, pre_class); } fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\t\tClassify:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total, 100.*class_correct/total); free(id); free_image(orig); free_image(sized); }
void validate_yolo(char *datacfg, char *cfgfile, char *weightfile) { list *options = read_data_cfg(datacfg); //char *train_list = option_find_str(options, "train", "data/train_list.txt"); //char *test_list = option_find_str(options, "test", "data/test_list.txt"); char *valid_list = option_find_str(options, "valid", "data/valid_list.txt"); //char *backup_directory = option_find_str(options, "backup", "/backup/"); //char *label_list = option_find_str(options, "labels", "data/labels_list.txt"); //int classes = option_find_int(options, "classes", 2); //char **labels = get_labels(label_list); network net = parse_network_cfg(cfgfile); if(weightfile){ load_weights(&net, weightfile); } 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)); char *base = "results/comp4_det_test_"; list *plist = get_paths(valid_list); char **paths = (char **)list_to_array(plist); layer l = net.layers[net.n-1]; int classes = l.classes; int square = l.sqrt; int side = l.side; int j; FILE **fps = calloc(classes, sizeof(FILE *)); for(j = 0; j < classes; ++j){ char buff[1024]; snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]); fps[j] = fopen(buff, "w"); } box *boxes = calloc(side*side*l.n, sizeof(box)); float **probs = calloc(side*side*l.n, sizeof(float *)); for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *)); int m = plist->size; int i=0; int t; float thresh = .001; int nms = 1; float iou_thresh = .5; int nthreads = 2; 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; 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); } time_t start = time(0); 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; float *predictions = network_predict(net, X); int w = val[t].w; int h = val[t].h; convert_yolo_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0); if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh); print_yolo_detections(fps, id, boxes, probs, side*side*l.n, classes, w, h); free(id); free_image(val[t]); free_image(val_resized[t]); } } fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start)); }
void validate_yolo_recall(char *cfgfile, char *weightfile) { network net = parse_network_cfg(cfgfile); if(weightfile){ load_weights(&net, weightfile); } 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)); char *base = "results/comp4_det_test_"; list *plist = get_paths("data/voc.2007.test"); char **paths = (char **)list_to_array(plist); layer l = net.layers[net.n-1]; int classes = l.classes; int square = l.sqrt; int side = l.side; int j, k; FILE **fps = calloc(classes, sizeof(FILE *)); for(j = 0; j < classes; ++j){ char buff[1024]; #ifndef _MSC_VER snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]); #else sprintf_s(buff, 1024, "%s%s.txt", base, voc_names[j]); #endif fps[j] = fopen(buff, "w"); } box *boxes = calloc(side*side*l.n, sizeof(box)); float **probs = calloc(side*side*l.n, sizeof(float *)); for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *)); int m = plist->size; int i=0; float thresh = .001; float iou_thresh = .5; float nms = 0; int total = 0; int correct = 0; int proposals = 0; float avg_iou = 0; for(i = 0; i < m; ++i){ char *path = paths[i]; image orig = load_image_color(path, 0, 0); image sized = resize_image(orig, net.w, net.h); char *id = basecfg(path); float *predictions = network_predict(net, sized.data); convert_yolo_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1); if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms); char *labelpath = find_replace(path, "images", "labels"); labelpath = find_replace(labelpath, "JPEGImages", "labels"); labelpath = find_replace(labelpath, ".jpg", ".txt"); labelpath = find_replace(labelpath, ".JPEG", ".txt"); int num_labels = 0; box_label *truth = read_boxes(labelpath, &num_labels); for(k = 0; k < side*side*l.n; ++k){ if(probs[k][0] > thresh){ ++proposals; } } for (j = 0; j < num_labels; ++j) { ++total; box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h}; float best_iou = 0; for(k = 0; k < side*side*l.n; ++k){ float iou = box_iou(boxes[k], t); if(probs[k][0] > thresh && iou > best_iou){ best_iou = iou; } } avg_iou += best_iou; if(best_iou > iou_thresh){ ++correct; } } fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total); free(id); free_image(orig); free_image(sized); } }