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

min() function with vol:cuda() #50

Open

Sarah20187 opened this issue Mar 21, 2018 · 1 comment

Sarah20187 commented Mar 21, 2018

after updating cudnn (v4 to v6), I found that the result of min() changed a lot in x range (parameter: -sm_terminate cnn).

Author

Sarah20187 commented Mar 22, 2018

I found the problem is caused by this

vol = torch.CudaTensor(1, disp_max, output:size(3), output:size(4)):fill(0/0);

different cudnn version set different values wiht '0/0'. So I just simply changed it to a large value and the problem solved. @jzbontar

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment