Reconstruction-by-inpainting-for-visual-anomaly-detection icon indicating copy to clipboard operation
Reconstruction-by-inpainting-for-visual-anomaly-detection copied to clipboard

About testing.

Open RohDonghyeon opened this issue 3 years ago • 1 comments

Thanks for providing the nice code.

With my custom dataset, the training proceeds without any problems.

But when running the test image i have a problem like the picture above.

If it's a problem with the number of channels, then learning shouldn't be happening, but what is the reason that learning is progressing, but only testing is not progressing?

RohDonghyeon avatar Jul 05 '21 07:07 RohDonghyeon

Hi, @RohDonghyeon Sorry for replying so late. Please check this https://github.com/plutoyuxie/Reconstruction-by-inpainting-for-visual-anomaly-detection/blob/7c0aaf90708c4db3b780ea5e20a1d8e752d897ff/datasets/mvtec.py#L56 mask = Image.open(mask).convert('1')

plutoyuxie avatar Sep 15 '21 08:09 plutoyuxie