Claim is misleading. CNN is not slower. The CNN implementation is slow.

[geyang]

The claim in this article and the notebook is quite misleading.

pyTorch CNN implementation already uses the cuDNN or a faster fbfft module. For smaller kernel sizes, the Winograd algorithm is even faster.

Your comparison is against convolution done in the position space, using a python for loop.

[eduardo4jesus]

pyTorch CNN implementation already uses the cuDNN or a faster fbfft module

@geyang. Could you link that code from pytorch's github? I am very interested in that and I couldn't find that yet.