Closed cscyangj closed 6 years ago
Your input file has three channels. If it is rgb or three channel grayscale u want to compress to one channel.
So if we need to processing RGB image, we need processing it per-channel?
It is okay when i use General_100, which is also RGB image, i think it is not related to gray image.
Ur images are inputting as three channel for some reason u might want to check dimensions using numpy. On Thu, Mar 15, 2018 at 11:27 AM cscyangj notifications@github.com wrote:
It is okay when i use General_100, which is also RGB image, i think it is not related to gray image.
— You are receiving this because you commented.
Reply to this email directly, view it on GitHub https://github.com/jmiller656/EDSR-Tensorflow/issues/24#issuecomment-373416234, or mute the thread https://github.com/notifications/unsubscribe-auth/ATogiDCAGKSPQrzDlHVMXFcuTAuT6N-mks5teohLgaJpZM4SsKTG .
@PrathamSoni , thanks for your help.
Why this happen, do we need grey image?
where train_600x600_to_800x800/data is the image for training.