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

Question about the time spent in Evaluation #154

Open
cs911 opened this issue Jul 7, 2022 · 1 comment
Open

Question about the time spent in Evaluation #154

cs911 opened this issue Jul 7, 2022 · 1 comment

Comments

@cs911
Copy link

cs911 commented Jul 7, 2022

During the Evaluation phase (evaluate fid prdc of the model) when I train the model, sometimes it takes ten minutes, sometimes two or three hours. And the gpu utilization is sometimes very high and sometimes very low. Why? My gpu is 2080ti.

@cs911 cs911 changed the title problem with the time spent in Evaluation Question about the time spent in Evaluation Jul 7, 2022
@alex4727
Copy link
Collaborator

alex4727 commented Jul 19, 2022

Hi,
FID and IS evaluation codes are mostly composed of GPU (CUDA) codes so they work faster.
PRDC on the other hand, tends to take longer time as it runs on CPU.
Besides, the size of dataset increases computing time of PRDC a lot more than FID so you should consider omitting PRDC if your dataset is too big or you don't need them.

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