Open madenburak opened 1 year ago
idp and idr value is same, also idp and precision or idr and recall value is same too. I don't understand this issue.
I used this code snippet:
track_lines = np.loadtxt(track_txt_path, delimiter=" ") ground_ids = [] track_ids = [] for frame in range(len(ground_lines)): gt_dets = [ground_lines[frame, :]] # select all detections in gt t_dets = [track_lines[frame, :]] # select all detections in t C = mm.distances.iou_matrix(gt_dets, t_dets, \ max_iou=0.5) # format: gt, t #Normally, there is must include ids of object in txt file ground_ids.append(frame) track_ids.append(frame) acc.update([ground_ids[frame]], [track_ids[frame]], C) mh = mm.metrics.create() summary = mh.compute(acc, metrics=['num_frames', 'idf1', 'idp', 'idr', \ 'recall', 'precision', 'num_objects', \ 'mostly_tracked', 'partially_tracked', \ 'mostly_lost', 'num_false_positives', \ 'num_misses', 'num_switches', \ 'num_fragmentations', 'mota', 'motp' \ ], \ name='acc') strsummary = mm.io.render_summary( summary, #formatters={'mota' : '{:.2%}'.format}, namemap={'idf1': 'IDF1', 'idp': 'IDP', 'idr': 'IDR', 'recall': 'Rcll', \ 'precision': 'Prcn', 'num_objects': 'GT', \ 'mostly_tracked' : 'MT', 'partially_tracked': 'PT', \ 'mostly_lost' : 'ML', 'num_false_positives': 'FP', \ 'num_misses': 'FN', 'num_switches' : 'IDsw', \ 'num_fragmentations' : 'FM', 'mota': 'MOTA', 'motp' : 'MOTP', \ } ) print(strsummary)
idp and idr value is same, also idp and precision or idr and recall value is same too. I don't understand this issue.
I used this code snippet: