SumayyaInayat comments

Repositories
Issues
Comments

Results 3 comments of


                                            SumayyaInayat

Training Error!

Hi, You can fix the above bug by changing the line number 288 in loss.py indices.append((b, a, gj.clamp_(0, gain[3].long() - 1), gi.clamp_(0, gain[2].long() - 1))) just add .long() to gain[3]...

Training Error!

Hi, Good that it worked! As for the multiple AP values values in the list, I think they are per sample (image in validation set) ap values. But for overall...

Getting nan loss for a custom dataset

Thanks for helping. I figured out. Few labels were missing. Thanks& Regards!