Fast Fourier transform support in PyTorch

#1

I am trying to implement Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding. For bilinear pooling, they use FFT and IFFT. But I couldn’t find documentation for FFT in PyTorch, will FFT operation be added to the library later or is it already implemented and not available in the documentation.

#2

What about https://github.com/locuslab/pytorch_fft?

1 Like
#3

@QuantScientist, @smth It has an autograd issue, https://github.com/locuslab/pytorch_fft/issues/4.

#4

The autograd issue seems to be fixed now.

1 Like
#5

@AashishV were you able to implement it?

#6

No, I just saw the issue was solved yesterday. Also, I am working on different projects now. So, I will not be able to do it for some time now.

#7

I have implemented a model here. Currently training it to see if results match.

#8

fft and ifft will be available in next release

#9

hi, how could I useFFT in the unstable version now, because it could not be install by pip or conda?thank you!

#10

You can install from source or wait for a couple days for the next release.