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
Why there will be predict_boxes not fit (boxes[:, 2:] >= boxes[:, :2]).all() sometimes even when I set seed.
Is this my mistake of train data or a bug?
The text was updated successfully, but these errors were encountered:
hank you so much for your interest in our work!
Yes, we actually encountered this situation during training as well, but it happens with an extremely, extremely low probability and is very hard to reproduce. For now, I’m not entirely sure of the exact reason behind it. If you have a better explanation, we’d be very grateful!
Why there will be predict_boxes not fit (boxes[:, 2:] >= boxes[:, :2]).all() sometimes even when I set seed.
Is this my mistake of train data or a bug?
The text was updated successfully, but these errors were encountered: