DeepVoltaire/AutoAugment

TypeError: function takes exactly 1 argument (3 given)

kentaroy47 opened this issue · 2 comments

downgrading to 6.1 fixed the problem.

may want to leave notes in the readme that 7.0.0 doesn't work.

actually it might not be a pillow version issue..
will get back to it after debug

File "/home/ken/miniconda3/envs/detectron/lib/python3.7/site-packages/PIL/Image.py", line 2505, in new
    return im._new(core.fill(mode, size, color))
TypeError: function takes exactly 1 argument (3 given)

torchvision transforms seems to have a bug with grayscale images.
converting it to RGB fixed the issue.

pytorch/vision#1776