search

jmiller656 / EDSR-Tensorflow

Tensorflow implementation of Enhanced Deep Residual Networks for Single Image Super-Resolution
MIT License
330 stars 107 forks source link

ValueError: could not broadcast input array from shape (50,50,3) into shape (50,50) #24

Closed cscyangj closed 6 years ago

cscyangj commented 6 years ago

Why this happen, do we need grey image?

python train.py --dataset train_600x600_to_800x800/data

where train_600x600_to_800x800/data is the image for training.

PrathamSoni commented 6 years ago

Your input file has three channels. If it is rgb or three channel grayscale u want to compress to one channel.

cscyangj commented 6 years ago

So if we need to processing RGB image, we need processing it per-channel?

cscyangj commented 6 years ago

It is okay when i use General_100, which is also RGB image, i think it is not related to gray image.

PrathamSoni commented 6 years ago

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 .

cscyangj commented 6 years ago

@PrathamSoni , thanks for your help.