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

Reproducibility of RFB speed #46

Closed
underfitting opened this issue Oct 11, 2018 · 1 comment
Closed

Reproducibility of RFB speed #46

underfitting opened this issue Oct 11, 2018 · 1 comment

Comments

@underfitting
Copy link

Hi,

I think you should add torch.cuda.synchronize() inside timer(e.g. after net(x) ), because CUDA is asynchronous.
By adding this, I got ~0.12s/forward.
@GOATmessi8
Copy link
Owner

The current inference time measurement followed as faster rcnn. Moreover, each forward only process a single image at test, so we do not need synchronize to depress the power of CUDA.

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
2 participants
@GOATmessi8 @underfitting