How to find more boundaries?

genforce / interfacegan

[CVPR 2020] Interpreting the Latent Space of GANs for Semantic Face Editing

https://genforce.github.io/interfacegan/

MIT License

1.51k stars 281 forks source link

How to find more boundaries? #19

Closed doantientai closed 5 years ago

doantientai commented 5 years ago

Congratulations for the great work!

Please correct me if I'm wrong. From what I understand, providing a pretrained model and a boundary (in boundaries/) we can tuning features of generated images. This is amazing.

I wonder if I can explore other boundaries as well? Let's say, hair color or skin colors? If it is possible, how could I do that?

Thank you very much!

ShenYujun commented 5 years ago

Yes, you can do that as long as you have a corresponding model for hair color (or skin color) classification. Then you can treat the boundary search process as a bi-classification problem (e.g. black hair v.s. blond hair).

Please see tool train_boundary.py as well as the function train_boundary() in file utils/manipulator.py for more details.

doantientai commented 5 years ago

Thank you @ShenYujun , I will try that

kLamda commented 4 years ago

@doantientai Were you able to generate new boundaries?

pfeducode commented 1 year ago

@doantientai你能创造新的界限吗？

Can you communicate with me