New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Jump to bottom

nan gradients with BCHW layout #13

Open

jj0mst opened this issue Jun 22, 2017 · 0 comments

Assignees

Labels

bug

Contributor

jj0mst commented Jun 22, 2017

I recently tried to use the new BCHW functions with my network, since i always use that layout and it simplifies my code.

I noticed that all the gradients of my convolutional layers are nan now, which makes also the weights full of nan after the parameters' update.

I'm sure i made all the necessary conversions and i get no error like inconsistency between tensors or anything else.

fxia22 self-assigned this

fxia22 added the bug label

# for free to join this conversation on GitHub. Already have an account? # to comment