search

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

Attributes predictor #23

Closed muxgt closed 5 years ago

muxgt commented 5 years ago

Hi! Thanks for your great research! Is there any chance you can provide attributes predictor that you used for finding boundaries? I didn't really get about scores that it should give to attributes on the pictures. Also for example for binary attributes like glasses/no glasses is it possible to manually put labels of say 1 for glasses, 0 for no glasses and feed this data to train a new boundary?

ShenYujun commented 5 years ago

Sorry that we will not release the attribute model. However, you can manually label a collection of synthesized images and then train a linear boundary for further manipulation.

muxgt commented 5 years ago

So is there a format of what labels should be? Or 1 and 0 will be OK?

ShenYujun commented 5 years ago

Yes, 0/1 is enough.

muxgt commented 5 years ago

OK, thanks!

kLamda commented 4 years ago

@muxgt Were you able to determine the attribute scores?