Avoid repeating the kernel

[f-dangel]

Currently the one-hot kernel is an identical copy for each input channel. This is not necessary when treating the channel in the input like a batch dimension. Besides smaller memory required to store the kernel, this optimization could also lead to run time speedups as the convolution operation will use groups=1 instead of groups=in_channels; I read somewhere that grouped convolutions are slower than ungrouped ones (I don't know the reason and never checked it).

[f-dangel]

I benchmarked three approaches:

• 1 group: This turned out to be the slowest, and (surprisingly) also used most memory, even though the one-hot kernel is not repeated at all
• C_in groups: This is the approach used in 0.0.1. It shows similar performance to the next approach, but uses a one-hot kernel which only uses 1 / N times the memory.
• C_in * N groups: Shows similar performance to the approach with C_in groups, but uses a much larger one-hot kernel.

For now, I will stay with the C_in groups strategy. In the future, there could be a switch allowing choosing one of the three approaches, but I have not encountered a practical use case yet.