CornerNet-Lite icon indicating copy to clipboard operation
CornerNet-Lite copied to clipboard

Published 20 hours ago • verified publisher icon princeton-vl

Train Loss Problem

Open DataXujing opened this issue 5 years ago • 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?

DataXujing avatar Dec 04 '19 03:12 DataXujing

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

float4189 avatar Dec 19 '19 12:12 float4189

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.

DataXujing avatar Dec 19 '19 13:12 DataXujing

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

float4189 avatar Dec 19 '19 13:12 float4189