How to train a classifier to get attribute scores

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 train a classifier to get attribute scores #97

Closed UdonDa closed 2 years ago

UdonDa commented 2 years ago

Hi, I trained resnet18 using a celeba dataset with a multi-label setting. And, I used it to find boundaries.

However, my results show that the generated images have an entangled boundary. The image used an only 'makeup' class. From left to right, the scalar weight of boundary is increased.

So, I guess that the training strategy of the classifier is different from your paper. Would you provide the detail how to train a classifier? Thanks.

UdonDa commented 2 years ago

Oh, I miss your conditional manipulation method...

AMEERAZAM08 commented 2 years ago

can you send your repo link please ... ?