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

On which machine the network was learned? #19

Closed
agnieszkajust opened this issue Mar 12, 2021 · 4 comments
Closed

On which machine the network was learned? #19

agnieszkajust opened this issue Mar 12, 2021 · 4 comments

Comments

@agnieszkajust
Copy link

I am trying to learn the network on gpu (RTX 2060) with batch = 1 but the computer starts humming and turns off. On which machine the network was learned? Can I change some parameter to the training on my computer starts correctly?

@csbhr
Copy link
Owner

csbhr commented Mar 12, 2021

We trained the network on TITAN RTX whose GPU memory is 24G.

@csbhr
Copy link
Owner

csbhr commented Mar 12, 2021

You can take a smaller patch-size, but the performance may be limited.

@agnieszkajust
Copy link
Author

In other computer I have installed cuda 11.0. When I was running training network I got "AttributeError: module 'cupy' has no attribute 'util'". Do I have to install other drivers and cude to run training?

@agnieszkajust
Copy link
Author

I solve it.

@csbhr csbhr closed this as completed May 8, 2021
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