| | |
| | | #ifdef OPENCV |
| | | #include "opencv2/highgui/highgui_c.h" |
| | | #include "opencv2/core/core_c.h" |
| | | //#include "opencv2/core/core.hpp" |
| | | #include "opencv2/core/version.hpp" |
| | | #include "opencv2/imgproc/imgproc_c.h" |
| | | |
| | | #ifndef CV_VERSION_EPOCH |
| | | #include "opencv2/videoio/videoio_c.h" |
| | |
| | | if (ymax > h) ymax = h; |
| | | |
| | | for(j = 0; j < classes; ++j){ |
| | | int class = j; |
| | | if (probs[i][class]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j+1, probs[i][class], |
| | | int class_id = j; |
| | | if (probs[i][class_id]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j+1, probs[i][class_id], |
| | | xmin, ymin, xmax, ymax); |
| | | } |
| | | } |
| | |
| | | return 0; |
| | | } |
| | | |
| | | void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile) |
| | | void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float thresh_calc_avg_iou) |
| | | { |
| | | int j; |
| | | list *options = read_data_cfg(datacfg); |
| | | char *valid_images = option_find_str(options, "valid", "data/train.list"); |
| | | char *valid_images = option_find_str(options, "valid", "data/train.txt"); |
| | | char *difficult_valid_images = option_find_str(options, "difficult", NULL); |
| | | 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; |
| | |
| | | fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay); |
| | | srand(time(0)); |
| | | |
| | | char *base = "comp4_det_test_"; |
| | | list *plist = get_paths(valid_images); |
| | | char **paths = (char **)list_to_array(plist); |
| | | |
| | | char **paths_dif = NULL; |
| | | if (difficult_valid_images) { |
| | | list *plist_dif = get_paths(difficult_valid_images); |
| | | paths_dif = (char **)list_to_array(plist_dif); |
| | | } |
| | | |
| | | |
| | | layer l = net.layers[net.n - 1]; |
| | | int classes = l.classes; |
| | | |
| | |
| | | args.h = net.h; |
| | | args.type = IMAGE_DATA; |
| | | |
| | | //const float thresh_calc_avg_iou = 0.24; |
| | | float avg_iou = 0; |
| | | int tp_for_thresh = 0; |
| | | int fp_for_thresh = 0; |
| | | |
| | | box_prob *detections = calloc(1, sizeof(box_prob)); |
| | | int detections_count = 0; |
| | | int unique_truth_index = 0; |
| | | int unique_truth_count = 0; |
| | | |
| | | int *truth_classes_count = calloc(classes, sizeof(int)); |
| | | |
| | |
| | | } |
| | | for (t = 0; t < nthreads && i + t - nthreads < m; ++t) { |
| | | const int image_index = i + t - nthreads; |
| | | char *path = paths[i + t - nthreads]; |
| | | char *path = paths[image_index]; |
| | | char *id = basecfg(path); |
| | | float *X = val_resized[t].data; |
| | | network_predict(net, X); |
| | |
| | | truth_classes_count[truth[j].id]++; |
| | | } |
| | | |
| | | // difficult |
| | | box_label *truth_dif = NULL; |
| | | int num_labels_dif = 0; |
| | | if (paths_dif) |
| | | { |
| | | char *path_dif = paths_dif[image_index]; |
| | | |
| | | char labelpath_dif[4096]; |
| | | find_replace(path_dif, "images", "labels", labelpath_dif); |
| | | find_replace(labelpath_dif, "JPEGImages", "labels", labelpath_dif); |
| | | find_replace(labelpath_dif, ".jpg", ".txt", labelpath_dif); |
| | | find_replace(labelpath_dif, ".JPEG", ".txt", labelpath_dif); |
| | | find_replace(labelpath_dif, ".png", ".txt", labelpath_dif); |
| | | truth_dif = read_boxes(labelpath_dif, &num_labels_dif); |
| | | } |
| | | |
| | | for (i = 0; i < (l.w*l.h*l.n); ++i) { |
| | | |
| | | int class_id; |
| | |
| | | detections[detections_count - 1].p = prob; |
| | | detections[detections_count - 1].image_index = image_index; |
| | | detections[detections_count - 1].class_id = class_id; |
| | | detections[detections_count - 1].truth_flag = 0; |
| | | detections[detections_count - 1].unique_truth_index = -1; |
| | | |
| | | int truth_index = -1; |
| | | float max_iou = 0; |
| | |
| | | float current_iou = box_iou(boxes[i], t); |
| | | if (current_iou > iou_thresh && class_id == truth[j].id) { |
| | | if (current_iou > max_iou) { |
| | | current_iou = max_iou; |
| | | truth_index = unique_truth_index + j; |
| | | max_iou = current_iou; |
| | | truth_index = unique_truth_count + j; |
| | | } |
| | | } |
| | | } |
| | | |
| | | // best IoU |
| | | if (truth_index > -1) { |
| | | detections[detections_count - 1].truth_flag = 1; |
| | | detections[detections_count - 1].unique_truth_index = truth_index; |
| | | } |
| | | else { |
| | | // if object is difficult then remove detection |
| | | for (j = 0; j < num_labels_dif; ++j) { |
| | | box t = { truth_dif[j].x, truth_dif[j].y, truth_dif[j].w, truth_dif[j].h }; |
| | | float current_iou = box_iou(boxes[i], t); |
| | | if (current_iou > iou_thresh && class_id == truth_dif[j].id) { |
| | | --detections_count; |
| | | break; |
| | | } |
| | | } |
| | | } |
| | | |
| | | // calc avg IoU, true-positives, false-positives for required Threshold |
| | | if (prob > thresh_calc_avg_iou) { |
| | | if (truth_index > -1) { |
| | | avg_iou += max_iou; |
| | | ++tp_for_thresh; |
| | | } |
| | | else |
| | | fp_for_thresh++; |
| | | } |
| | | } |
| | | } |
| | | } |
| | | |
| | | unique_truth_index += num_labels; |
| | | unique_truth_count += num_labels; |
| | | |
| | | free(id); |
| | | free_image(val[t]); |
| | |
| | | } |
| | | } |
| | | |
| | | avg_iou = avg_iou / (tp_for_thresh + fp_for_thresh); |
| | | |
| | | |
| | | // SORT(detections) |
| | | qsort(detections, detections_count, sizeof(box_prob), detections_comparator); |
| | |
| | | for (i = 0; i < classes; ++i) { |
| | | pr[i] = calloc(detections_count, sizeof(pr_t)); |
| | | } |
| | | printf("detections_count = %d, unique_truth_index = %d \n", detections_count, unique_truth_index); |
| | | printf("detections_count = %d, unique_truth_count = %d \n", detections_count, unique_truth_count); |
| | | |
| | | |
| | | int *truth_flags = calloc(unique_truth_index, sizeof(int)); |
| | | int *truth_flags = calloc(unique_truth_count, sizeof(int)); |
| | | |
| | | int rank; |
| | | for (rank = 0; rank < detections_count; ++rank) { |
| | |
| | | pr[d.class_id][rank].fp++; // false-positive |
| | | } |
| | | |
| | | |
| | | for (i = 0; i < classes; ++i) |
| | | { |
| | | const int tp = pr[i][rank].tp; |
| | |
| | | } |
| | | } |
| | | } |
| | | //printf("point = %d, cur_recall = %.4f, cur_precision = %.4f \n", point, cur_recall, cur_precision); |
| | | //printf("class_id = %d, point = %d, cur_recall = %.4f, cur_precision = %.4f \n", i, point, cur_recall, cur_precision); |
| | | |
| | | avg_precision += cur_precision; |
| | | } |
| | | avg_precision = avg_precision / 11; |
| | | printf("class = %d, name = %s, \t ap = %2.2f %% \n", i, names[i], avg_precision*100); |
| | | printf("class_id = %d, name = %s, \t ap = %2.2f %% \n", i, names[i], avg_precision*100); |
| | | mean_average_precision += avg_precision; |
| | | } |
| | | |
| | | const float cur_precision = (float)tp_for_thresh / ((float)tp_for_thresh + (float)fp_for_thresh); |
| | | const float cur_recall = (float)tp_for_thresh / ((float)tp_for_thresh + (float)(unique_truth_count - tp_for_thresh)); |
| | | const float f1_score = 2.F * cur_precision * cur_recall / (cur_precision + cur_recall); |
| | | printf(" for thresh = %1.2f, precision = %1.2f, recall = %1.2f, F1-score = %1.2f \n", |
| | | thresh_calc_avg_iou, cur_precision, cur_recall, f1_score); |
| | | |
| | | printf(" for thresh = %0.2f, TP = %d, FP = %d, FN = %d, average IoU = %2.2f %% \n", |
| | | thresh_calc_avg_iou, tp_for_thresh, fp_for_thresh, unique_truth_count - tp_for_thresh, avg_iou * 100); |
| | | |
| | | mean_average_precision = mean_average_precision / classes; |
| | | printf("\n mean average precision (mAP) = %f, or %2.2f %% \n", mean_average_precision, mean_average_precision*100); |
| | | |
| | |
| | | fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start)); |
| | | } |
| | | |
| | | void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh) |
| | | #ifdef OPENCV |
| | | void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final_height) |
| | | { |
| | | printf("\n num_of_clusters = %d, final_width = %d, final_height = %d \n", num_of_clusters, final_width, final_height); |
| | | |
| | | //float pointsdata[] = { 1,1, 2,2, 6,6, 5,5, 10,10 }; |
| | | float *rel_width_height_array = calloc(1000, sizeof(float)); |
| | | |
| | | list *options = read_data_cfg(datacfg); |
| | | char *train_images = option_find_str(options, "train", "data/train.list"); |
| | | list *plist = get_paths(train_images); |
| | | int number_of_images = plist->size; |
| | | char **paths = (char **)list_to_array(plist); |
| | | |
| | | int number_of_boxes = 0; |
| | | printf(" read labels from %d images \n", number_of_images); |
| | | |
| | | int i, j; |
| | | for (i = 0; i < number_of_images; ++i) { |
| | | char *path = paths[i]; |
| | | char labelpath[4096]; |
| | | 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, ".png", ".txt", labelpath); |
| | | int num_labels = 0; |
| | | box_label *truth = read_boxes(labelpath, &num_labels); |
| | | //printf(" new path: %s \n", labelpath); |
| | | for (j = 0; j < num_labels; ++j) |
| | | { |
| | | number_of_boxes++; |
| | | rel_width_height_array = realloc(rel_width_height_array, 2 * number_of_boxes * sizeof(float)); |
| | | rel_width_height_array[number_of_boxes * 2 - 2] = truth[j].w * final_width; |
| | | rel_width_height_array[number_of_boxes * 2 - 1] = truth[j].h * final_height; |
| | | printf("\r loaded \t image: %d \t box: %d", i+1, number_of_boxes); |
| | | } |
| | | } |
| | | printf("\n all loaded. \n"); |
| | | |
| | | //int number_of_boxes = 10; |
| | | CvMat* points = cvCreateMat(number_of_boxes, 2, CV_32FC1); |
| | | CvMat* centers = cvCreateMat(num_of_clusters, 2, CV_32FC1); |
| | | CvMat* labels = cvCreateMat(number_of_boxes, 1, CV_32SC1); |
| | | |
| | | for (i = 0; i < number_of_boxes; ++i) { |
| | | points->data.fl[i * 2] = rel_width_height_array[i * 2]; |
| | | points->data.fl[i * 2 + 1] = rel_width_height_array[i * 2 + 1]; |
| | | //cvSet1D(points, i * 2, cvScalar(rel_width_height_array[i * 2], 0, 0, 0)); |
| | | //cvSet1D(points, i * 2 + 1, cvScalar(rel_width_height_array[i * 2 + 1], 0, 0, 0)); |
| | | } |
| | | |
| | | |
| | | const int attemps = 1000; |
| | | double compactness; |
| | | |
| | | enum { |
| | | KMEANS_RANDOM_CENTERS = 0, |
| | | KMEANS_USE_INITIAL_LABELS = 1, |
| | | KMEANS_PP_CENTERS = 2 |
| | | }; |
| | | |
| | | printf("\n calculating k-means++ ..."); |
| | | // Should be used: distance(box, centroid) = 1 - IoU(box, centroid) |
| | | cvKMeans2(points, num_of_clusters, labels, |
| | | cvTermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 1000, 0), attemps, |
| | | 0, KMEANS_RANDOM_CENTERS, |
| | | centers, &compactness); |
| | | |
| | | printf("\n"); |
| | | printf("anchors = "); |
| | | for (i = 0; i < num_of_clusters; ++i) { |
| | | printf("%2.2f,%2.2f, ", centers->data.fl[i * 2], centers->data.fl[i * 2 + 1]); |
| | | } |
| | | |
| | | //for (i = 0; i < number_of_boxes; ++i) |
| | | // printf("%2.2f,%2.2f, ", points->data.fl[i * 2], points->data.fl[i * 2 + 1]); |
| | | |
| | | free(rel_width_height_array); |
| | | cvReleaseMat(&points); |
| | | cvReleaseMat(¢ers); |
| | | cvReleaseMat(&labels); |
| | | } |
| | | #else |
| | | void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final_height) { |
| | | printf(" k-means++ can't be used without OpenCV, because there is used cvKMeans2 implementation \n"); |
| | | } |
| | | #endif // OPENCV |
| | | |
| | | void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, int dont_show) |
| | | { |
| | | list *options = read_data_cfg(datacfg); |
| | | char *name_list = option_find_str(options, "names", "data/names.list"); |
| | |
| | | if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms); |
| | | draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes); |
| | | save_image(im, "predictions"); |
| | | show_image(im, "predictions"); |
| | | if (!dont_show) { |
| | | show_image(im, "predictions"); |
| | | } |
| | | |
| | | free_image(im); |
| | | free_image(sized); |
| | | free(boxes); |
| | | free_ptrs((void **)probs, l.w*l.h*l.n); |
| | | #ifdef OPENCV |
| | | cvWaitKey(0); |
| | | cvDestroyAllWindows(); |
| | | if (!dont_show) { |
| | | cvWaitKey(0); |
| | | cvDestroyAllWindows(); |
| | | } |
| | | #endif |
| | | if (filename) break; |
| | | } |
| | |
| | | |
| | | void run_detector(int argc, char **argv) |
| | | { |
| | | int dont_show = find_arg(argc, argv, "-dont_show"); |
| | | int http_stream_port = find_int_arg(argc, argv, "-http_port", -1); |
| | | char *out_filename = find_char_arg(argc, argv, "-out_filename", 0); |
| | | char *prefix = find_char_arg(argc, argv, "-prefix", 0); |
| | | float thresh = find_float_arg(argc, argv, "-thresh", .24); |
| | | int cam_index = find_int_arg(argc, argv, "-c", 0); |
| | | int frame_skip = find_int_arg(argc, argv, "-s", 0); |
| | | int num_of_clusters = find_int_arg(argc, argv, "-num_of_clusters", 5); |
| | | int final_width = find_int_arg(argc, argv, "-final_width", 13); |
| | | int final_heigh = find_int_arg(argc, argv, "-final_heigh", 13); |
| | | if(argc < 4){ |
| | | fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]); |
| | | return; |
| | |
| | | if(weights) |
| | | if (weights[strlen(weights) - 1] == 0x0d) weights[strlen(weights) - 1] = 0; |
| | | char *filename = (argc > 6) ? argv[6]: 0; |
| | | if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh); |
| | | if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, dont_show); |
| | | 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); |
| | | else if(0==strcmp(argv[2], "recall")) validate_detector_recall(datacfg, cfg, weights); |
| | | else if(0==strcmp(argv[2], "map")) validate_detector_map(datacfg, cfg, weights); |
| | | else if(0==strcmp(argv[2], "map")) validate_detector_map(datacfg, cfg, weights, thresh); |
| | | else if(0==strcmp(argv[2], "calc_anchors")) calc_anchors(datacfg, num_of_clusters, final_width, final_heigh); |
| | | else if(0==strcmp(argv[2], "demo")) { |
| | | list *options = read_data_cfg(datacfg); |
| | | int classes = option_find_int(options, "classes", 20); |
| | |
| | | char **names = get_labels(name_list); |
| | | if(filename) |
| | | if (filename[strlen(filename) - 1] == 0x0d) filename[strlen(filename) - 1] = 0; |
| | | demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename); |
| | | demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename, |
| | | http_stream_port, dont_show); |
| | | } |
| | | } |