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

Training error #39

Closed
wangq95 opened this issue May 26, 2019 · 2 comments
Closed

Training error #39

wangq95 opened this issue May 26, 2019 · 2 comments

Comments

@wangq95
Copy link

wangq95 commented May 26, 2019

Hi, @DrSleep , I am appreciate for your works, but when I directly run the scripts named train/nyu.sh, it run on three NVIDIA 1080ti cards but got blocked when evaluating the trained model after 16 epoches, I tried to change the value of num_workers in src/config.py from 16 to 1, it still occurred. But, when I set it to zero, it works, the training procedure would not be blocked, can you enplane it? Thanks a lot.
@DrSleep
Copy link
Owner

DrSleep commented Jun 29, 2019

can you try to add this line "cv2.setNumThreads(0)" here ?
there was an issue before with PyTorch and cv2 multi-processing, might be that

@DrSleep
Copy link
Owner

DrSleep commented Aug 11, 2019

closing it for now. feel free to comment in case you still experience the problem

@DrSleep DrSleep closed this as completed Aug 11, 2019
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
@DrSleep @wangq95