Ask about train hairstyles

[panghongwei17]

Hi，

When I train my own hairstyle model, do I need to convert the images under the --hairstyle_ref_img_train_path=/path/to/celeba_hq_train \ parameter into latents through the e4e algorithm. So instead of --latents_train_path=/path/to/train_faces.pt \

[wty-ustc]

The hairstyle_ref_img_train_path needs to be provided with images. Can you provide more information about the error?