wildcat.pytorch icon indicating copy to clipboard operation
wildcat.pytorch copied to clipboard

Published 20 hours ago • verified publisher icon durandtibo

Training stuck at 0%

Open Tauranis opened this issue 7 years ago • 2 comments

I'm currently using a docker image which include all required pytorch and CUDA 8.0 dependencies. I just cloned the repo and executed the demo_voc2007 with the default argument values. The training stuck at 0%, nothing happens. Is there a known reason why is this happening?

Tauranis avatar Sep 04 '17 16:09 Tauranis

This usually happens when the batch size is large, like 32 or Can it 64. Can it be due to the multiprocessing done internally?

Tauranis avatar Sep 04 '17 16:09 Tauranis

Hi Tauranis, I encountered the same problem as you. Do you have any solution now?

Kqiii avatar Sep 07 '18 05:09 Kqiii