Skip to content
New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Jump to bottom

Not training in DIGITS #6

Closed
achaiah opened this issue Nov 18, 2016 · 4 comments
Closed

Not training in DIGITS #6

achaiah opened this issue Nov 18, 2016 · 4 comments

Comments

@achaiah
Copy link

achaiah commented Nov 18, 2016

Hi, I was wondering if you tried running the models in NVIDIA DIGITS? I imported one of your models (resnet 36) - it runs but does not train. Any ideas?

Thanks!
@jay-mahadeokar
Copy link
Owner

I haven't tried it. What do you mean by does not train? Can you be more specific?

@achaiah
Copy link
Author

achaiah commented Nov 21, 2016

It literally doesn't train (i.e. zero progress over 200 epochs). I found a fix here: BVLC/caffe#3919 There's a difference in BatchNorm between bvlc and NVIDIA that is confusing.

@achaiah achaiah closed this as completed Nov 21, 2016
@mrgloom
Copy link

mrgloom commented Nov 26, 2016 •
edited
Loading

@achaiah Can you be more specific about differences in BN layer?
Seems realted thread is here ? NVIDIA/DIGITS#629

@achaiah
Copy link
Author

achaiah commented Nov 27, 2016

The thread you pointed to is correct as well... same issue. The CUDNN BN implementation has changed and that has broken existing nets that use BN.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@jay-mahadeokar @achaiah @mrgloom