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

the change of smile when increase the distance of the "glasses" attribute #26

Closed zzxzzx123 closed 5 years ago

zzxzzx123 commented 5 years ago

Hi,thanks for your great research. I have a problem when I apply the "pggan_celebahq_eyeglasses_c_age_gender_boundary.npy" on the pre-trained pggan model. With the conditional manipulation on "glasses" attribute , the smile changes gradually. Here are the results. 000_001 000_004 008_001 008_005 But the attributes seem to be uncorrelated in your paper. Could you explained it for me?

ShenYujun commented 5 years ago

The eyeglasses attribute for PGGAN may not be that accurate, since there are not enough faces with eyeglasses among synthesized data. According to the boundary correlation, however, they should be disentangled with each other.

zzxzzx123 commented 5 years ago

Thanks for your answer. I will train a svm classifier to test it again.