Channel size

[vkothapally]

DDFPack and DDFUpPack currently assume that the in_channels and out_channels are the same. Can you make short changes to the modules to allow them to work for different in_channels and out_channels?

Also, I had an issue when I tried using DDFPack for input with single-channel (eg. input with dimensions [10,1,256,256] ) Can you please let me know if there is something I'm missing out on?

[theFoxofSky]

1. In theory, DDF decouples dynamic depth-wise convolution, so it cannot change the number of channels, you can append a 1x1 convolution after DDF to change the number of channels.

2. What happened when feeding single-channel inputs