Antonio Lutfi

In object_tracker.py you first do `detections = [Detection(bbox, score, class_name, feature) for bbox, score, class_name, feature in zip(converted_boxes, scores[0], names, features)]` and then `indices = preprocessing.non_max_suppression(boxs, classes, nms_max_overlap, scores)` I...

Since, in a graph batch(GB), there are no edges between individual graphs, once batch_num_nodes is set for GB, automatically calculate batch_num_edges by calling set_bath_num_edges with no arguments, or something like...