You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
batch_ious=self._batch_iou(box_preds, gt_boxes) # (B, N, M)
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?
The text was updated successfully, but these errors were encountered:
WormCoder
changed the title
iou(pred_box, truth_box) of iou(prior_box, truth_box) should be calculated here?
iou(pred_box, truth_box) or iou(prior_box, truth_box) should be calculated here?
Sep 11, 2018
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.
gluon-cv/gluoncv/model_zoo/yolo/yolo_target.py
Line 193 in 9669d72
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?
The text was updated successfully, but these errors were encountered: