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

correlation function runs very slow #40

Closed
sczhou opened this issue Mar 7, 2018 · 2 comments
Closed

correlation function runs very slow #40

sczhou opened this issue Mar 7, 2018 · 2 comments

Comments

@sczhou
Copy link

sczhou commented Mar 7, 2018

Hi, In training the FlowNetC, the correlation layer runs so slow, It's about 5.5s a batch (batch size = 8) on TiTanX, I don't know whether there are some problems, and could you give me some advice for fast training? Thanks!
@fitsumreda
Copy link
Contributor

@sczhou the issue was that non optimal number of threads per block were used for the backward function of the correlation layer, hence the slow speed.
it is now faster by about 5x.

@fitsumreda
Copy link
Contributor

mode details in the commit 94b023

@laaRaa laaRaa mentioned this issue Sep 14, 2018
Open
@toprocker toprocker mentioned this issue Jan 2, 2019
Open
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
@sczhou @fitsumreda