Generative-Inpainting-pytorch

This is a pytorch version of the paper 'Generative Image Inpainting with Contextual Attention' (by Jiahui Yu et al. / 2018 CVPR)

Dependencies

python 3.6
pytorch 0.3.0

Link

paper: https://arxiv.org/abs/1801.07892
original TF code: https://github.com/JiahuiYu/generative_inpainting

Data

I used celebA faces dataset. (about 202,000 images)
place it in the 'data' directory

images=https://www.dropbox.com/s/3e5cmqgplchz85o/CelebA_nocrop.zip?dl=0
attributes: https://www.dropbox.com/s/auexdy98c6g7y25/list_attr_celeba.zip?dl=0 (just for getting file names)

Running code

python run.py

P.S

I made this network for catching up SOTA technique of the Image Inpainting area.
Though it trains without any bug, generated images are mostly blurry.

After clonning the repo, you need to check the contextual module performance or critics convergence.