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

RuntimeError: The size of tensor a (335) must match the size of tensor b (334) at non-singleton dimension 3 #12

Open
agnieszkajust opened this issue Nov 16, 2021 · 5 comments

Comments

@agnieszkajust
Copy link

I get "RuntimeError: The size of tensor a (335) must match the size of tensor b (334) at non-singleton dimension 3" during testing on my own data. How to solve it?

@chosj95
Copy link
Owner

chosj95 commented Nov 16, 2021

Hi,

I think you tested on the images of which size are not multiple of 4.
Because of the stride in our model, you should use the input image having sizes of multiple of 4.
If necessary, you should pad an input image and remove the padded area.

Which dataset did you test on?

@agnieszkajust
Copy link
Author

I tried to test on RealBlur - http://cg.postech.ac.kr/research/realblur/ .

@chosj95
Copy link
Owner

chosj95 commented Nov 16, 2021

Since the RealBlur dataset contains the images of which size are not multiple of 4, we also pad the input image and remove the padded area from the output image.

@agnieszkajust
Copy link
Author

Ok, I'll do it. Thanks.
Will be available a code to training MIMO-UNet++ soon?

@usutdzxych
Copy link

no results
image

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

3 participants