Sparse kernels for better performance?

f-dangel / unfoldNd

(N=1,2,3)-dimensional unfold (im2col) and fold (col2im) in PyTorch

MIT License

85 stars 7 forks source link

Sparse kernels for better performance? #5

Open f-dangel opened 3 years ago

f-dangel commented 3 years ago

The implementation of unfoldNd relies on one-hot convolution. This means the convolution kernels are highly sparse. Hence, the code could run faster when using sparse tensors.

Open questions:

What is the result of a sparse convolution with a dense input? If it's a dense tensor, that would be good.
Does using sparse tensors provide a benefit in terms of run time? (related: #4)

f-dangel commented 3 years ago

Sparse operations are currently not supported in PyTorch. Waiting for progress.