Neural Network Python Packages

torch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

spacy

💫 Industrial-strength Natural Language Processing (NLP) in Python

blis

💥 Fast matrix-multiplication as a self-contained Python library – no system dependencies!

onnx

Open standard for machine learning interoperability

tensorflow

An Open Source Machine Learning Framework for Everyone

ultralytics-thop

PyTorch model profiler for computing MACs and parameter counts to measure deep learning model complexity.

autograd

Efficiently computes derivatives of NumPy code.

gensim

Topic Modelling for Humans

kornia

🐍 Geometric Computer Vision Library for Spatial AI

tensorflow-cpu

An Open Source Machine Learning Framework for Everyone

mosaicml-streaming

A Data Streaming Library for Efficient Neural Network Training

paddlepaddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

pytorch-tokenizers

On-device AI across mobile, embedded and edge for PyTorch

pytorch-ignite

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

tf-nightly

An Open Source Machine Learning Framework for Everyone

torchtnt

A lightweight library for PyTorch training tools and utilities

poutyne

A simplified framework and utilities for PyTorch

onnx-weekly

Open standard for machine learning interoperability

multi-model-server

Multi Model Server is a tool for serving neural net models for inference

model-archiver

Multi Model Server is a tool for serving neural net models for inference

pennylane

PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

nnaudio

Audio processing by using pytorch 1D convolution network

neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.