search

wty-ustc / HairCLIP

[CVPR 2022] HairCLIP: Design Your Hair by Text and Reference Image
GNU Lesser General Public License v2.1
524 stars 68 forks source link

about pretrained unet infer #7

Closed eeric closed 2 years ago

eeric commented 2 years ago

mask_512 = (torch.unsqueeze(torch.max(labels_predict, 1)[1], 1)==13).float() 1.why hair equal 13, bg not equal 13? 2.unet infer results that have 19 channels, what did they means?

wty-ustc commented 2 years ago

Please refer to Face parsing.

eeric commented 2 years ago

ok, thanks.