-
Notifications
You must be signed in to change notification settings - Fork 28k
CTCLoss produces NaNs in some situations #14335
Copy link
Copy link
Closed
Labels
high prioritymodule: cudaRelated to torch.cuda, and CUDA support in generalRelated to torch.cuda, and CUDA support in generalmodule: determinismmodule: nnRelated to torch.nnRelated to torch.nntriagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module
Description
Metadata
Metadata
Assignees
Labels
high prioritymodule: cudaRelated to torch.cuda, and CUDA support in generalRelated to torch.cuda, and CUDA support in generalmodule: determinismmodule: nnRelated to torch.nnRelated to torch.nntriagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module
Type
Fields
Give feedbackNo fields configured for issues without a type.
🐛 Bug
when I train a cnn-rnn-ctc text recognize model, I meet nan loss after some iters, but it's ok at pytorch 0.4 with warpctc
To Reproduce
Steps to reproduce the behavior:
conda,pip, source): pip3