fft-conv-pytorch

fft-conv-pytorch

fkodom

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

494 Stars
60 Forks
494 Watchers
Python Language
mit License
Cost to Build
$7.3K
Market Value
$24.6K

Growth over time

8 data points  ·  2021-08-01 → 2025-04-01
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about fft-conv-pytorch

Question copied to clipboard

What is the fkodom/fft-conv-pytorch GitHub project? Description: "Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone fft-conv-pytorch

Clone via HTTPS

git clone https://github.com/fkodom/fft-conv-pytorch.git

Clone via SSH

[email protected]:fkodom/fft-conv-pytorch.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the fft-conv-pytorch issue tracker:

Open GitHub Issues