Grow your team on GitHub
GitHub is home to over 50 million developers working together. Join them to grow your own development teams, manage permissions, and collaborate on projects.
Sign upRepositories
-
ParlAI
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
-
habitat-sim
A flexible, high-performance 3D simulator for Embodied AI research.
-
pytorch-dp
Training PyTorch models with differential privacy
-
fvcore
Collection of common code that's shared among different research projects in FAIR computer vision team.
-
detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
-
hydra
Hydra is a framework for elegantly configuring complex applications
-
you2me
Inferring Body Pose in Egocentric Video via First and Second Person Interactions
-
nevergrad
A Python toolbox for performing gradient-free optimization
-
mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
-
hiplot
HiPlot makes understanding high dimensional data easy
-
ReAgent
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
-
ClassyVision
An end-to-end PyTorch framework for image and video classification
-
EGG
EGG: Emergence of lanGuage in Games
-
pifuhd
High-Resolution 3D Human Digitization from A Single Image.
-
habitat-challenge
Code for the habitat challenge
-
Mephisto
A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use
-
dagger
Experiment orchestration
-
pytorch3d
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
-
pyrobot
PyRobot: An Open Source Robotics Research Platform
-
pytext
A natural language modeling framework based on PyTorch
-
CrypTen
A framework for Privacy Preserving Machine Learning
-
dlrm
An implementation of a deep learning recommendation model (DLRM)
-
PyTorch-BigGraph
Generate embeddings from large-scale graph-structured data.
-
PoincareMaps
The need to understand cell developmental processes has spawned a plethora of computational methods for discovering hierarchies from scRNAseq data. However, existing techniques are based on Euclidean geometry which is not an optimal choice for modeling complex cell trajectories with multiple branches. To overcome this fundamental representation …
-
habitat-api
A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.
-
vilbert-multi-task
Multi Task Vision and Language
-
detr
End-to-End Object Detection with Transformers
-
flashlight
A C++ standalone library for machine learning
-
SentEval
A python tool for evaluating the quality of sentence embeddings.
-
SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.