princeton-vl/CornerNet-Lite

Train Loss Problem

DataXujing opened this issue · 3 comments

When I train my own data, used CornerNet_saccade model, but the loss do not decrease, in my training process. I do not known why, should I need a pre_trained model?

Hello! I also encountered the same problem,Did you solve it?

Hello! I also encountered the same problem,Did you solve it?

I do not Known how to treat it. I think, Pre-trained model could solve this problem.

OK,!thank you very much, which model are you using now?