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

What is the purpose of the U-Net generator? #55

Open
sgoerttler opened this issue Jan 3, 2019 · 2 comments
Open

What is the purpose of the U-Net generator? #55

sgoerttler opened this issue Jan 3, 2019 · 2 comments

Comments

@sgoerttler
Copy link

Hello,
currently I am implementing the CycleGAN with the Resnet generator for a medical application, and it yields very good results!
However, what is the purpose of the U-Net generator in the code? Does it work for image translation tasks, and if so, how do I get it to work? I tried it out, and it does not work at all for my case. As far as I know the U-Net is only used for segmentation tasks.

@luistelmocosta
Copy link

I have the same doubt

@uceclz0
Copy link

uceclz0 commented Jul 19, 2021

For my idea, encoder-decoder without skip connection may be more suitable for the style transfer task with unpaired datasets because the texture detail may not be key points in some cases. The U-Net may be great for paired datasets because it can supplement some feature information from different levels in the encoder.

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