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 testing on multi-scale #87

Open
wsh2836741 opened this issue Jan 31, 2018 · 4 comments
Open

Question about testing on multi-scale #87

wsh2836741 opened this issue Jan 31, 2018 · 4 comments

Comments

@wsh2836741
Copy link

Thanks for excellent work.But i am confused,it said 'out of memory' when i use titan xp GPU(12G).And the largest scale i can use is 1100*1100.Thank you in advice.

@MhLiao
Copy link
Owner

MhLiao commented Feb 1, 2018

Do you use cudnn? It should not suffer "out of memory" when the largest scale is 1600*1600 with a titan xp.

@wsh2836741
Copy link
Author

thx,i have solved the problem by using cudnn,and 8G is enough.

@larklili
Copy link

hello,when I run demo.py.It has the following errors:
F0510 10:28:22.312146 15884 syncedmem.cpp:56] Check failed: error == cudaSuccess (2 vs. 0) out of memory
what should i do?I have changed the scales,like this:
scales=((300,300),(700,700),(700,500),(700,300),(1100,1100))

@sungwonida
Copy link

Do you use cudnn? It should not suffer "out of memory" when the largest scale is 1600*1600 with a titan xp.

Thank you. USE_CUDNN := 1 solved the issue.

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

4 participants