fkodom/fft-conv-pytorch

fft-conv-pytorch

✅ Recently maintained

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

524Stars
61Forks
07-day stars

Python · MIT · Last push 2026-10-16

Official repository & installation ↗
pytorchpython3convolutionimage-processingneural-networks

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-05524
2026-10-06524
2026-10-07524
2026-10-08524
2026-10-09524
2026-10-10524
2026-10-11524
2026-10-12524
2026-10-13524
2026-10-14524
2026-10-15524
2026-10-16524
2026-10-17524
2026-10-18524
2026-10-19524
2026-10-20524
2026-10-21524
2026-10-22524
2026-10-23524
2026-10-24524
2026-10-25524
2026-10-26524
2026-10-27524
2026-10-28524
2026-10-29524
2026-10-30524
2026-10-31524
2026-11-01524
2026-11-02524
2026-11-03524

Get the project

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

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

kornia

Differentiable geometric computer vision library on PyTorch, offering image transforms, camera models and feature matching as neural network layers for spatial

★ 12,227opencv

Open Source Computer Vision Library

★ 91,417supervision

Reusable computer vision tools for object detection annotations and metrics.

★ 51,469