void *detect_in_thread(void *ptr) { float nms = .4; detection_layer l = net.layers[net.n-1]; float *X = det_s.data; float *prediction = network_predict(net, X); memcpy(predictions[demo_index], prediction, l.outputs*sizeof(float)); mean_arrays(predictions, FRAMES, l.outputs, avg); free_image(det_s); convert_detections(avg, 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:%.1f\n",fps); printf("Objects:\n\n"); images[demo_index] = det; det = images[(demo_index + FRAMES/2 + 1)%FRAMES]; demo_index = (demo_index + 1)%FRAMES; draw_detections(det, l.side*l.side*l.n, demo_thresh, boxes, probs, demo_names, demo_labels, demo_classes); return 0; }
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.rows*l.cols*l.n, sizeof(box)); float **probs = calloc(l.rows*l.cols*l.n, sizeof(float *)); for(j = 0; j < l.rows*l.cols*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(input,0,0,net.c); 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_detections(predictions, l.classes, l.n, l.sqrt, l.rows, l.cols, 1, 1, thresh, probs, boxes, 0); if (nms) do_nms_sort(boxes, probs, l.rows*l.cols*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.rows*l.cols*l.n, thresh, boxes, probs, voc_names, voc_labels, CLASSNUM); save_image(im, "predictions"); show_image(im, "predictions"); show_image(sized, "resized"); free_image(im); free_image(sized); #ifdef OPENCV cvWaitKey(0); cvDestroyAllWindows(); #endif if (filename) break; } }
void validate_coco_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("/home/pjreddie/data/voc/test/2007_test.txt"); 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, coco_classes[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; int nms = 0; float iou_thresh = .5; float nms_thresh = .5; 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_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_thresh); 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); } }
void validate_coco(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/"; list *plist = get_paths("data/coco_val_5k.list"); //list *plist = get_paths("/home/pjreddie/data/people-art/test.txt"); //list *plist = get_paths("/home/pjreddie/data/voc/test/2007_test.txt"); 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; char buff[1024]; _snprintf(buff, 1024, "%s/coco_results.json", base); FILE *fp = fopen(buff, "w"); fprintf(fp, "[\n"); 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 = .01; int nms = 1; float iou_thresh = .5; int nthreads = 8; 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]; int image_id = get_coco_image_id(path); float *X = val_resized[t].data; float *predictions = network_predict(net, X); int w = val[t].w; int h = val[t].h; convert_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_cocos(fp, image_id, boxes, probs, side*side*l.n, classes, w, h); free_image(val[t]); free_image(val_resized[t]); } } fseek(fp, -2, SEEK_CUR); fprintf(fp, "\n]\n"); fclose(fp); fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start)); }
void validate_yolo_recall(char *cfgfile, char *weightfile, char *val_images, char *out_dir, float th, int log, int draw) { 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)); //create output directory if it does not exist struct stat st= {0}; if(stat(out_dir,&st)==-1){ fprintf(stderr,"Creating output directory\n"); mkdir(out_dir,0700); } char *base = out_dir; list *plist = get_paths(val_images); 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 rows = l.rows; int cols = l.cols; 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(rows*cols*l.n, sizeof(box)); float **probs = calloc(rows*cols*l.n, sizeof(float *)); for(j = 0; j < rows*cols*l.n; ++j) probs[j] = calloc(classes, sizeof(float *)); int m = plist->size; int i=0; float thresh = th; float iou_thresh[11] = {0.0,0.05,0.1,0.15,0.20,0.25,0.30,0.35,0.40,0.45,0.5}; float nms = 0.1; int total = 0; int correct[11] = {0,0,0,0,0,0,0,0,0,0,0}; int proposals = 0; float avg_iou = 0; Vector id_found; Vector id_invalid; initArray(&id_found,5); initArray(&id_invalid,5); for(i = 0; i < m; ++i){ char * image_path = strtok(paths[i]," "); char * label_path = strtok(NULL," "); image orig = load_image(image_path, 0, 0,net.c); image color; if(draw) color = load_image(image_path, 0, 0, 3); image sized = resize_image(orig, net.w, net.h); //char *id = basecfg(path); float *predictions = network_predict(net, sized.data); convert_detections(predictions, classes, l.n, square, rows, cols, 1, 1, thresh, probs, boxes, 0); if (nms) do_nms(boxes, probs, rows*cols*l.n, 1, nms); int num_labels = 0; box_label *truth = read_boxes(label_path, &num_labels); int old_p = proposals; for(k = 0; k < rows*cols*l.n; ++k){ if(probs[k][0] > thresh){ ++proposals; } } if(old_p!=proposals){ if(log){ char filename[256]; sprintf(filename, "%s/%d.txt", base,i); printf("log in file %s\n",filename); FILE * out = fopen(filename, "w"); fprintf(out,"W\tH\tX\tY\n"); for(k=0; k<rows*cols*l.n; ++k){ if(probs[k][0] > thresh){ fprintf(out, "%f\t%f\t%f\t%f\n",boxes[k].w,boxes[k].h,boxes[k].x,boxes[k].y); } } fclose(out); } if(draw){ draw_detections(color, l.rows*l.cols*l.n, thresh, boxes, probs, voc_names, voc_labels, CLASSNUM); show_image(color, "predictions"); #ifdef OPENCV cvWaitKey(0); //cvDestroyAllWindows(); #endif } } for (j = 0; j < num_labels; ++j) { ++total; while(id_found.used <= truth[j].id){ insertArray(&id_invalid,0); insertArray(&id_found,0); } if(truth[j].classe > CLASSNUM-1) id_invalid.array[truth[j].id]=1; box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h}; float best_iou = 0; for(k = 0; k < rows*cols*l.n; ++k){ float iou = box_iou(boxes[k], t); //find overlapping prediction if(iou > best_iou){ //find the predicted class float best_score = thresh; int best_class_index = -1; for(int c=0; c<CLASSNUM; c++){ if(probs[k][c]>best_score){ best_score = probs[k][c]; best_class_index = c; } } //check if it's good or not if(best_class_index == truth[j].classe) best_iou = iou; } } avg_iou += best_iou; for(int k=0; k<11; k++){ if(best_iou > iou_thresh[k]){ id_found.array[truth[j].id]=1; ++correct[k]; } } } if(i%10==0){ printf("\033[2J"); printf("\033[1;1H"); printf("#img\tPred\tTP\ttot\tRPs/Img\tAvg-IOU\tRecall\tPrecision\n"); printf("%5d\t%5d\t%5d\t%5d\t%.2f\t%.2f%%\t%.2f%%\t%.2f%%\n", i, proposals, correct[10], total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct[10]/total, 100.*correct[10]/proposals); printf("IOU_th\tTP\tFP\tRecall\tPrecision\n"); for(int k=0; k<11; k++){ printf("%.2f%%\t%5d\t%5d\t%.2f%%\t%.2f%%\t\n", iou_thresh[k], correct[k], proposals-correct[k], 100.*correct[k]/total, 100.*correct[k]/proposals); } int found=0; int invalid = 0; for(int i=0; i<id_found.used; i++){ if(id_invalid.array[i]!=1) found+=id_found.array[i]; invalid+=id_invalid.array[i]; } printf("Founded: %d/%d\t%d\n", found, id_found.used-invalid,invalid); } //free(id); free_image(orig); free_image(sized); } for(j = 0; j < classes; ++j){ fprintf(fps[j],"IOU_th;TP;FP;Recall;Precision\n"); for(int k=0; k<11; k++){ fprintf(fps[j],"%.2f%%;%5d;%5d;%.2f%%;%.2f%%;\n", iou_thresh[k], correct[k], proposals-correct[k], 100.*correct[k]/total, 100.*correct[k]/proposals); } fprintf(fps[j], "\n\nFounded;Total;\n"); int found=0; int invalid = 0; for(int i=0; i<id_found.used; i++){ if(id_invalid.array[i]!=1) found+=id_found.array[i]; invalid+=id_invalid.array[i]; } fprintf(fps[j], "%d;%d;\n", found, id_found.used-invalid); fclose(fps[j]); } freeArray(&id_found); }
void validate_yolo(char *cfgfile, char *weightfile, char *val_images, char *result_dir) { 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)); //create output directory if it does not exist struct stat st= {0}; if(stat(result_dir,&st)==-1){ fprintf(stderr,"Creating output directory\n"); mkdir(result_dir,0700); } char *base = result_dir; list *plist = get_paths(val_images); 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 rows = l.rows; int cols = l.cols; 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(rows*cols*l.n, sizeof(box)); float **probs = calloc(rows*cols*l.n, sizeof(float *)); for(j = 0; j < rows*cols*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_detections(predictions, classes, l.n, square, rows, cols, w, h, thresh, probs, boxes, 0); if (nms) do_nms_sort(boxes, probs, rows*cols*l.n, classes, iou_thresh); print_yolo_detections(fps, id, boxes, probs, rows*cols*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)); }