iou(pred_box, truth_box) or iou(prior_box， truth_box) should be calculated here?

[WormCoder]

https://github.com/dmlc/gluon-cv/blob/9669d728d17715586765a9f2b1886fc054e1d6ed/gluoncv/model_zoo/yolo/yolo_target.py#L193

In the yolov3's paper, ignore_threshold if for the iou between prior(or anchor) box and truth box, i.e. the iou(prior_box， truth_box), so why do you use iou(pred_box, truth_box) here?

[zhreshold]

The order is swapped by transpose. The reason to use it in reverse order is because anchors are of batch size 1, and by doing this we can save batch_size times the computation.