PyTorch

Axfacebook/Ax

An accessible, general-purpose platform for understanding, managing, deploying, and automating adaptive experiments using Bayesian and bandit optimization.

Auto-PyTorchautoml/Auto-PyTorch

Automatic neural architecture search and hyperparameter optimization for PyTorch, focusing on tabular data and time series forecasting.

Alibi DetectSeldonIO/alibi-detect

A Python library for outlier, adversarial, and drift detection in machine learning models, supporting tabular, text, image, and time series data.

hyperlearndanielhanchen/hyperlearn

HyperLearn provides 2-2000x faster machine learning algorithms with 50% less memory usage, optimized for all hardware.

Texarasyml/texar

A modular toolkit for machine learning, natural language processing, and text generation with TensorFlow and PyTorch versions.

waveglowNVIDIA/waveglow

A flow-based generative network for fast, high-quality speech synthesis from mel-spectrograms.

Objectrongoogle-research-datasets/Objectron

A large-scale dataset of object-centric video clips with 3D bounding box annotations and AR metadata for 3D object detection research.

ESM3evolutionaryscale/esm

A multimodal protein language model for generative protein design and engineering by jointly reasoning over sequence, structure, and function.

rlpytastooke/rlpyt

A modular, high-throughput PyTorch framework for deep reinforcement learning research, supporting policy gradient, deep Q-learning, and Q-function policy gradient algorithms.

RoseTTAFoldRosettaCommons/RoseTTAFold

A deep learning system for accurate protein structure and interaction prediction using a three-track neural network.

Raster Visionazavea/raster-vision

An open source Python library and framework for building computer vision models on satellite, aerial, and large imagery sets.

CellposeMouseLand/cellpose

A generalist algorithm for cellular segmentation with human-in-the-loop training and superhuman generalization across diverse microscopy images.

garage - A toolkit for reproducible reinforcement learning researchrlworkgroup/garage

A toolkit and library for developing, evaluating, and reproducing reinforcement learning algorithms.

cvxpylayerscvxgrp/cvxpylayers

A Python library for constructing differentiable convex optimization layers in PyTorch, JAX, and MLX using CVXPY.

robosatmapbox/robosat

An end-to-end Python pipeline for semantic segmentation of aerial and satellite imagery to extract features like buildings and roads.

Chai-1chaidiscovery/chai-lab

A multi-modal foundation model for state-of-the-art molecular structure prediction of proteins, small molecules, DNA, RNA, and glycosylations.

Atlasmagicleap/Atlas

An end-to-end deep learning system for reconstructing complete 3D scenes (geometry and semantics) from posed 2D images.

aitextgenminimaxir/aitextgen

A Python package for fine-tuning and generating text with GPT-2 and GPT Neo models using PyTorch and Hugging Face Transformers.

AI Explainability 360IBM/AIX360

An open-source Python toolkit providing a comprehensive collection of algorithms for interpreting and explaining machine learning models and datasets.

Votenetfacebookresearch/votenet

An end-to-end 3D object detection network that uses deep point set networks and Hough voting to directly detect objects in point clouds.

PyTorch Lightning BoltsPyTorchLightning/pytorch-lightning-bolts

A collection of models, callbacks, and datasets to extend PyTorch Lightning for applied AI/ML research and production.

ImitationHumanCompatibleAI/imitation

Clean PyTorch implementations of imitation and reward learning algorithms for reinforcement learning.

PyTorchNetpytorch/tnt

A lightweight library providing PyTorch training tools and utilities to simplify and standardize training loops.

ProteinMPNNdauparas/ProteinMPNN

A deep learning model for protein sequence design that generates amino acid sequences for given protein backbones.

SciBERTallenai/scibert

A BERT language model pre-trained on a large corpus of scientific papers for natural language processing tasks in scientific domains.

BindsNETHananel-Hazan/bindsnet

A Python library for simulating spiking neural networks (SNNs) using PyTorch, geared towards biologically inspired machine learning.

d3rlpytakuseno/d3rlpy

A Python library for offline deep reinforcement learning with support for state-of-the-art algorithms and user-friendly APIs.

pytorch_tabularmanujosephv/pytorch_tabular

A unified framework for implementing and training deep learning models on tabular data using PyTorch and PyTorch Lightning.

Subs AIabdeladim-s/subsai

A versatile tool for generating, translating, and syncing subtitles from audio/video using Whisper and other AI models via Web UI, CLI, or Python.

Talosautonomio/talos

A Python library for automated hyperparameter optimization and model evaluation with TensorFlow, Keras, and PyTorch.

totalVIscverse/scvi-tools

A Python library for deep probabilistic modeling and analysis of single-cell and spatial omics data.

Det3Dpoodarchu/Det3D

A general-purpose PyTorch codebase for 3D object detection with state-of-the-art model implementations and multi-dataset support.

scGPTbowang-lab/scGPT

A transformer-based foundation model pretrained on millions of single-cell profiles for generative AI tasks in single-cell multi-omics.

Big Transfer (BiT)google-research/big_transfer

Official repository for Big Transfer (BiT) models, providing pre-trained visual representations for efficient transfer learning across computer vision tasks.