search

f-dangel / unfoldNd

(N=1,2,3)-dimensional unfold (im2col) and fold (col2im) in PyTorch
MIT License
82 stars 6 forks source link

Add a benchmark #4

Closed f-dangel closed 3 years ago

f-dangel commented 3 years ago

To get an idea of how well the one-hot convolution approach performs in comparison with the PyTorch implementation there should be a run time evaluation.

Open questions: