About the dataset

[czyczyczy]

when i read the LQGT_dataset.py, i found that
if self.opt['color']: # change color space if necessary
img_GT = util.channel_convert(img_GT.shape[2], self.opt['color'], [img_GT])[0]
the img_GT.shape[2] is 3
the self.opt['color'] is RGB in train_SRResNet.yml
but the def channel_convert in util.py
if in_c == 3 and tar_type == 'gray': # BGR to gray
gray_list = [cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) for img in img_list]
return [np.expand_dims(img, axis=2) for img in gray_list]
elif in_c == 3 and tar_type == 'y': # BGR to y
y_list = [bgr2ycbcr(img, only_y=True) for img in img_list]
return [np.expand_dims(img, axis=2) for img in y_list]
elif in_c == 1 and tar_type == 'RGB': # gray/y to BGR
return [cv2.cvtColor(img, cv2.COLOR_GRAY2BGR) for img in img_list]
else:
return img_list

has no in_c=3 and tar_type == 'RGB',so it just return img_list。
Is the means when i use DIV2K, i don't need to deal with the conversion among BGR, gray and y?

[xinntao]

Yes, if you want to train on RGB channels and you use the DIV2K, then no conversion is needed.
The conversion is executed when you have RGB images, but you want to train on gray images.

[czyczyczy]

Yes, if you want to train on RGB channels and you use the DIV2K, then no conversion is needed.
The conversion is executed when you have RGB images, but you want to train on gray images.

Thank you very much for your answer .