FFDNet how can num_input_channels=15 in training step and 3 in test step?

how can num_input_channels=15 in training step and 3 in test step?

Open HymEric opened this issue 5 years ago • 1 comments

Thanks for your work. But I have a question about how can num_input_channels=15 in training step and 3 in test step?

Apr 02 '19 03:04 HymEric

The 3-channel image is first reshaped to 12-channel sub-images by a PixelUnshuffle layer.

Apr 02 '19 06:04 cszn