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.

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

How to predict with model trained with multiple GPUs? #446

Closed
YaoZhang93 opened this issue Dec 25, 2020 · 2 comments
Closed

How to predict with model trained with multiple GPUs? #446

YaoZhang93 opened this issue Dec 25, 2020 · 2 comments

Comments

@YaoZhang93
Copy link

YaoZhang93 commented Dec 25, 2020

Hi Fabian,

I trained a nnU-Net with 2 GPUs following the instruction:
image

When I predict using this model by:
image

I got a error:
image

Did I get it wrong?
Do you have any suggestion to make predictions with a multi-gpu model?

Thanks,
Yao

@YaoZhang93
Copy link
Author

The problem is located here:
image
The multi-gpu model accept different initial variables.
I bypass the problem by manually define these variables.

@FabianIsensee
Copy link
Member

The multi-GPU implementation is not very good at the moment which I why i explicitly recommend not to use it ;-) This is something I need to improve in the future.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants