Testing results are not as expected

[SURABHI-GUPTA]

@xiefan-guo Hey. Thanks for releasing the codebase.

I tested your pretrained model on celeba, however, the results are not as expected. Even the identity of the person belongs to the training set, still it does not generalize well. What could be the reason?

[xiefan-guo]

Hi, maybe it is caused by the preprocessing of the image. We follow the experimental settings of EdgeConnect. For CelebA, we cropped the center 178x178 of the images, then resized them to 256x256 using bilinear interpolation.

[haolin512900]

Hi, maybe it is caused by the preprocessing of the image. We follow the experimental settings of EdgeConnect. For CelebA, we cropped the center 178x178 of the images, then resized them to 256x256 using bilinear interpolation.
How to solve this problem please？

[FavorMylikes]

Hi, maybe it is caused by the preprocessing of the image. We follow the experimental settings of EdgeConnect. For CelebA, we cropped the center 178x178 of the images, then resized them to 256x256 using bilinear interpolation.

How to solve this problem please？

Have you solve this problem?