Convolution Python Packages

mnn

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

einconv

Convolutions and more as einsum for PyTorch

fft-conv-pytorch

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

torchnd

ND convolutions, complex convolutions, ND padding, etc

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.

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.

pytsetlinmachinecuda

Massively Parallel and Asynchronous Architecture for Logic-based AI

indexedconv

Code for the indexed convolution

graphtsetlinmachine

Tsetlin Machine for Logical Learning and Reasoning With Graphs

conv

A lightweight library to do for-loop-styled convolution passes on your iterable objects (e.g.: on a list). Note: this is not a convolution, it is about exposing what would the kernel pass on in the first place in your loops.

sphericalrht

Spherical implementation of the Rolling Hough Transform

debugui

DebugUI python sdk

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.

atc-torch

atc-torch - Pytorch

simplefilter

Python module for image convolution and ML classification.

mnncv

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

numpynet

Convolutional Neural Network written from scratch using numpy with API similar to tensorflow.

mnncompress

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

numpycnn

Building Convolutional Neural Networks From Scratch using NumPy

octconv

Octave Convolution Implementation in PyTorch

licpy

Line Integral Convolution

ndc

Numerical differentiation leveraging convolutions based on PyTorch