genforce/interfacegan

Can you provide the pre-trained attributes prediction model to me?

wty-ustc opened this issue · 5 comments

wty-ustc commented

In your paper, you claimed This model is trained with multi-task losses to simultaneously predict smile, age, gender, eyeglasses, as well as the 5-point facial landmarks. Can you provide me with this model? Thank you very much!

GaParmar commented

I would also find this very useful

ShenYujun commented

Please try models here.

  • 👍6
ucalyptus2 commented

@ShenYujun these were for celebahq, anything for ffhq? Will both work the same ways since both have similar brilliant facial capabilities?

lizaitang commented

Please try models here.

Thanks, I used this classfiers to test the result, but the prediction logits seems different each time, have you met the same issue?

federicoromeo commented

Can anyone provide a code snippet to make those classifiers work?
I followed stylegan's and even stylespace's (see my issue for details) but i can't make those work!