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

Identical images generated by scheme I in Fig 5 of Extended paper #8

Open
SunYangtian opened this issue Mar 26, 2020 · 1 comment
Open

Comments

@SunYangtian
Copy link

Hi!
I'm not very clear that why the scheme I can only generate identical images on the horse to zebra translation task. Is it because the same attention network from x to y and from y to x ? Or is it because the nework only produces one content mask?
Does scheme I only work in facial expression transfer task? I'm confused because cycle gan can work in all thess situations.

@stillstream
Copy link

I have the same confusion.Do you solve it ?@SunYangtian

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

2 participants