Face_Enhancement usage guide about bringing-old-photos-back-to-life HOT 3 CLOSED

How can I run Face Enhancement on a custom image?

I tried this command:

cd Face_Enhancement
python -m test_face --dataroot ./datasets/faces/ --netG pix2pixhd --gpu_ids 0

but the results are all-gray images.

same results: all-gray.
do you know why? if so , could you please tell me how to fix it?

from bringing-old-photos-back-to-life.

I found it seem need a label? but how to generate the label is not mentioned in Readme and Jouranl paper.

line26 of Face_Enhancement/data/face_dataset.py

        image_path = os.path.join(opt.dataroot, opt.old_face_folder)
        label_path = os.path.join(opt.dataroot, opt.old_face_label_folder)

from bringing-old-photos-back-to-life.

The face enhancement model should always be used jointly with the global restoration model. This is because during training the face enhancement model only sees the restored images.

from bringing-old-photos-back-to-life.