Awesome Python Data Science

An Open Source Machine Learning Framework for Everyone

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Open Source Computer Vision Library

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Caffe: a fast open framework for deep learning.

Visualizer for neural network, deep learning and machine learning models

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

A game theoretic approach to explain the output of any machine learning model.

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）

Graph Neural Network Library for PyTorch

Open standard for machine learning interoperability

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

Image augmentation for machine learning experiments.

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

A toolkit for making real world machine learning and data analysis applications in C++

Python package built to ease deep learning on graph, on top of existing DL frameworks.

1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.

Low-code framework for building custom LLMs, neural networks, and other AI models

LAVIS - A One-stop Library for Language-Vision Intelligence

Fast and Accurate ML in 3 Lines of Code

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

TensorFlow-based neural network library

Deep learning library featuring a higher-level API for TensorFlow.

A python library for user-friendly forecasting and anomaly detection on time series.

AutoML library for deep learning

Deep universal probabilistic programming with Python and PyTorch

Efficiently computes derivatives of NumPy code.

Deep Learning and Reinforcement Learning Library for Scientists and Engineers

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

mlpack: a fast, header-only C++ machine learning library

Build Graph Nets in Tensorflow

Image augmentation library in Python for machine learning.

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

A unified, comprehensive and efficient recommendation library

Scalable and user friendly neural :brain: forecasting algorithms.

Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.

Models, data loaders and abstractions for language processing, powered by PyTorch

Accelerated deep learning R&D

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.

StellarGraph - Machine Learning on Graphs

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

Learning to Rank in TensorFlow

Automatic architecture search and hyperparameter optimization for PyTorch

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

Graph Neural Networks with Keras and Tensorflow 2.

Source-to-Source Debuggable Derivatives in Pure Python

Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).

Interpretability and explainability of data and machine learning models