Seitaro Shinagawa

Sorry for the late response. A simple workaround is as below, ## change train.py https://github.com/SeitaroShinagawa/chainer-partial_convolution_image_inpainting/blob/master/train.py#L92 ```python val_dataset = getattr(datasets, "place2_test")(paths.val_place2, mask_path="mask/256", flip=0, resize_to=args.resize_to, crop_to=args.crop_to) #val_iter = chainer.iterators.SerialIterator(val_dataset, 8) val_iter =...

Thanks for your interest. **Answer to the first question** As shown in https://github.com/SeitaroShinagawa/chainer-partial_convolution_image_inpainting/blob/master/common/net.py#L56, original images and masks are element-wise multiplied to get broken images "x*mask." You can replace this "x*mask"...

It seems because the external cropping loss of the cropping frame is ignored in my implementation. As discussed in #12, I think you can avoid this problem if you can...

Hi @liuguilin1225, thanks for your kind mention! I will check it. Seitaro

I added a statement to README, ["Difference from original paper."](https://github.com/SeitaroShinagawa/chainer-partial_convolution_image_inpainting#difference-from-original-paper) According to http://masc.cs.gmu.edu/wiki/partialconv, I fix my implementation. I added bias calculation in partial convolution layer (C(0) in FAQ)