output_padding (int or tuple, optional): Zero-padding added to one side of the output.
But I don’t really understand what this means.
Can some explain this with some examples?
think of ConvTranspose as the opposite operation of Conv and output_padding of ConvTranspose is input padding of Conv
I’m curious: if output_padding of ConvTranspose is input padding of Conv, why is it single-sided?
# input padding = 1 in Conv: [[ 0 0 0 ] [ 0 1 0 ] [ 0 0 0 ]] # but output padding = 1 in ConvTransposed: [[ 1 0 ] [ 0 0 ]]
output padding is assymmetric. it’s only applied in the right and the bottom of the image.