DiffBIR icon indicating copy to clipboard operation
DiffBIR copied to clipboard

Training stage 1 model under codeformer degradation on grayscale images

Open pihchikk opened this issue 1 year ago • 0 comments

I try to train the stage 1 model under codeformer degradation for CT-imagery SR using grayscale CT images. Specifying in_chans = 1 in swinir.yaml configuration file gives me "Given groups=1, weight of size [180, 64, 3, 3], expected input[4, 192, 98, 98] to have 64 channels, but got 192 channels instead" error. How do I update the code to train it using grayscale?

pihchikk avatar Oct 26 '23 13:10 pihchikk