How to generate "val_labels"?

tzt101 / MichiGAN

MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing (SIGGRAPH 2020)

MIT License

294 stars 39 forks source link

Closed Seraen closed 2 years ago

Seraen commented 2 years ago

Hi, I would like to use my own data of pictures, and I am wondering how to get the "val_labels"? Thank you!

Zlin0530 commented 1 year ago

Hi, did you solve the problem of how to get "val_labels", I also want to test it on my own dataset, but I don't know how to get "val_labels"

Seraen commented 1 year ago

Hi, you can use semantic segmentation to get the mask of hair, and the images should be converted to binary images (0 for black, 1 for white).