I am trying to implement a custom conv layer, so I need to process the input using im2col and col2im utilities to extract input patches according to the kernel size, stride and padding parameters. How to access these utilities in Pytorch ?
I am trying to implement a custom conv layer, so I need to process the input using im2col and col2im utilities to extract input patches according to the kernel size, stride and padding parameters. How to access these utilities in Pytorch ?