Awesome Python Data Science

🤗 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.

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.

Graph Neural Network Library for PyTorch

Open standard for machine learning interoperability

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

A very simple framework for state-of-the-art Natural Language Processing (NLP)

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

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

An elegant PyTorch deep reinforcement learning library.

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)

Deep universal probabilistic programming with Python and PyTorch

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

A scikit-learn compatible neural network library that wraps PyTorch

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

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.

A highly efficient implementation of Gaussian Processes in PyTorch

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

Fast, flexible and easy to use probabilistic modelling in Python.

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.

Accelerated deep learning R&D

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

Data manipulation and transformation for audio signal processing, powered by PyTorch

Automatic architecture search and hyperparameter optimization for PyTorch

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

A toolkit for reproducible reinforcement learning research.

An offline deep reinforcement learning library

Synthetic data generators for tabular and time-series data

OpenMMLab Foundational Library for Training Deep Learning Models

An autoML framework & toolkit for machine learning on graphs.

allRank is a framework for training learning-to-rank neural models based on PyTorch.

Pretrained model hub for Keras 3.

A PyTorch and TorchDrug based deep learning library for drug pair scoring. (KDD 2022)

Engine for AI/ML/Data tracking, visualization, explainability, drift detection, and dashboards for Polyaxon.

Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...

PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.

A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).