We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Hi, I had an error while feeding male2female test images (178x218) into test.py or test_batch.py.
RuntimeError: The size of tensor a (313) must match the size of tensor b (312) at non-singleton dimension 2
It seems that the aspect ratio is unintentionally kept during resizing, leading to (256, 313) output instead of (256, 256).
One way to fix this is changing new_size=config['new_size'] to new_size=(config['new_size'], config['new_size']) in the below line.
new_size=config['new_size']
new_size=(config['new_size'], config['new_size'])
ACL-GAN/test_batch.py
Line 65 in 7166a86
The text was updated successfully, but these errors were encountered:
In CouncilGAN, a center crop is applied for those images with h!=w, See
https://github.com/Onr/Council-GAN/blob/7fe8f8a72ab1b00d4024dd09f414f53781f27eaa/utils.py#L127
Guess this is also what we need?
Sorry, something went wrong.
Thanks for your suggestions! We did not test for images with h!=w, and thus there may be some errors. I think center crop should work.
No branches or pull requests
Hi,
I had an error while feeding male2female test images (178x218) into test.py or test_batch.py.
It seems that the aspect ratio is unintentionally kept during resizing, leading to (256, 313) output instead of (256, 256).
One way to fix this is changing
new_size=config['new_size']
tonew_size=(config['new_size'], config['new_size'])
in the below line.ACL-GAN/test_batch.py
Line 65 in 7166a86
The text was updated successfully, but these errors were encountered: