Open HymEric opened 5 years ago
Thanks for your work. But I have a question about how can num_input_channels=15 in training step and 3 in test step?
The 3-channel image is first reshaped to 12-channel sub-images by a PixelUnshuffle layer.
Thanks for your work. But I have a question about how can num_input_channels=15 in training step and 3 in test step?