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

Problem in the use of gpu/cpu #870

Closed
samymdihi opened this issue May 25, 2021 · 2 comments
Closed

Problem in the use of gpu/cpu #870

samymdihi opened this issue May 25, 2021 · 2 comments

Comments

@samymdihi
Copy link

I have a problem regarding the use of cpu/gpu. I have really good cpu/gpu but when I run demo_inference I reach 100% of the CPU all the time during the process and only 12% of the gpu is used. Do you know how I could increase the use of the gpu ? Is anyone facing the same issue ?

I am using the "support for pytorch 1.5.0" #592 branch, with cuda 11.3, python 3.9, pytorch 1.8.1, torchvision 0.9.1
@fortminors
Copy link

Same here. Have you managed to solve it?

@Fang-Haoshu
Copy link
Member

Hi, seems it currently consumes a lot of CPU in order to speed up. We haven't found a good way to solve it yet.

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
@Fang-Haoshu @fortminors @samymdihi