stylegan2-pytorch icon indicating copy to clipboard operation
stylegan2-pytorch copied to clipboard

PIL.unidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7ff1f05b62c0>

Open CatDogS opened this issue 2 years ago • 4 comments

After I created the lmdb dataset, I started training the model.This error will occur.My dataset is all .jpg files.

CatDogS avatar Apr 15 '22 08:04 CatDogS

I think some of your image files are not a valid jpeg files.

rosinality avatar Apr 17 '22 04:04 rosinality

Hii I also met this error while my dataset is all .png files. Have you solved this problem?

Yuxinn-J avatar Aug 11 '22 09:08 Yuxinn-J

i also met this. For me it was because output resolution of the lmdb was not the right one.

aRavanel avatar Oct 19 '22 07:10 aRavanel

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7ff527fa20e0> This is a problem I encountered when running train.py, my data set is in mbd format file, why do I still get an error? Is there a loss in the data set?

ASAmbitious avatar Sep 13 '23 08:09 ASAmbitious