zero Reg loss and bad results

[mingcv]

I'm training from scratch of EfficientDet-d0 on a dataset which contains 600 images to recognize insulators, which is the only one class. However, when I was both training and evaluating, the Reg loss keeps zero, and the Cls loss first declines then increases and then declines rapidly. Cannot figure out what's happening, is it for lack of data and overfitting happens? But will it bring zero Reg loss? After all, I'm using the minimum version of EfficientDet. Any help, plz!

[zylo117]

reg loss being so low means the anchors config don't fit your targets. You can refer to Q3 here. https://github.com/zylo117/Yet-Another-EfficientDet-Pytorch/issues/386

[myarchivedaccount]

I realize this problem due to unsuitable anchor and IOU. try modifying this line positive_indices = torch.ge(IoU_max, 0.4) --> positive_indices = torch.ge(IoU_max, 0.1) Thanks

[zylo117]

I realize this problem due to unsuitable anchor and IOU. try modifying this line positive_indices = torch.ge(IoU_max, 0.4) --> positive_indices = torch.ge(IoU_max, 0.1) Thanks

I don't think that's a proper solution, you should instead change anchor ratio to suit your datasets. @buidung2004