Convolution Python Packages

mnn

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

263K 16K 2K

fft-conv-pytorch

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

26K 522 62

einconv

Convolutions and more as einsum for PyTorch

22K 18 1

tmu

Implements the Tsetlin Machine, Coalesced Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features, drop clause, Type III Feedback, focused negative sampling, multi-task classifier, autoencoder, literal budget, and one-vs-one multi-class classifier. TMU is written in Python with wrappers for C and CUDA-based clause evaluation and updating.

2K 175 36

torchnd

ND convolutions, complex convolutions, ND padding, etc

2K 2 0

pytorch-hexagdly

Process hexagonally sampled data with PyTorch

1K 0 0

pytsetlinmachine

Implements the Tsetlin Machine, Embedding Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features, multigranularity, clause indexing, drop clause/literal, and literal budget.

848 153 33

pytsetlinmachinecuda

Massively Parallel and Asynchronous Architecture for Logic-based AI

807 44 4

keras-hexagdly

Keras 3 hexagonal CNN layers (HexagDLy port) for hexagonally-sampled data — IACT/Cherenkov cameras, etc. — Support for hls4ml in progress

733 0 0

indexedconv

An implementation of indexed convolution and pooling

654 16 10

graphtsetlinmachine

Graph Tsetlin Machine

499 54 19

georacoon

The GeoRacoon (GR) is out and about -- ready to tackle Geographic Raster

436 13 2

conv

A lightweight library to do for-loop-styled convolution passes on your iterable objects (e.g.: on a list).

427 7 2

pytsetlinmachineparallel

Multi-threaded implementation of the Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features and multigranularity.

366 43 10