Closed BrandonHanx closed 2 years ago
hey, thanks for the question. Yes that is expected.
Thanks for your reply.
How do you tackle these grayscale images in the training stage? Just repeat 3 channels for CNN's input?
from PIL import Image as PILImage
im = PILImage.open(img_dir)
rgb_im = im.convert('RGB')
I converted them to rgb using pillow
I see. This issue is solved for me. Thanks.
Hi, thanks for your great work.
I found there are many gray-scale images in the training set. Is this expected?
like
ac7f353fd7481926e8fa9eafed609948.jpg
,7d956f0919f2eab63e481e9321ce2028.jpg
and so on