Facebook Research (@facebookresearch)

Top repositories

1

llama

Inference code for LLaMA models
Python
44,989
star
2

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Jupyter Notebook
42,134
star
3

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Python
25,771
star
4

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Python
25,718
star
5

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Python
25,567
star
6

fastText

Library for fast text representation and classification.
HTML
24,973
star
7

faiss

A library for efficient similarity search and clustering of dense vectors.
C++
24,035
star
8

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
Python
19,691
star
9

codellama

Inference code for CodeLlama models
Python
13,303
star
10

detr

End-to-End Object Detection with Transformers
Python
11,076
star
11

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation
Jupyter Notebook
10,584
star
12

ParlAI

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
Python
10,085
star
13

maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
Python
9,104
star
14

pifuhd

High-Resolution 3D Human Digitization from A Single Image.
Python
8,923
star
15

hydra

Hydra is a framework for elegantly configuring complex applications
Python
8,550
star
16

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents
Python
8,088
star
17

AnimatedDrawings

Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
Python
8,032
star
18

ImageBind

ImageBind One Embedding Space to Bind Them All
Python
7,630
star
19

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger
Jupyter Notebook
7,402
star
20

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Python
7,322
star
21

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.
Jupyter Notebook
7,278
star
22

DensePose

A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
Jupyter Notebook
6,547
star
23

pytext

A natural language modeling framework based on PyTorch
Python
6,357
star
24

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
Python
5,995
star
25

metaseq

Repo for external large-scale work
Python
5,947
star
26

demucs

Code for the paper Hybrid Spectrogram and Waveform Source Separation
Python
5,886
star
27

SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
Python
5,678
star
28

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
Python
5,495
star
29

mmf

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
Python
5,235
star
30

ConvNeXt

Code release for ConvNeXt model
Python
4,971
star
31

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Python
4,830
star
32

AugLy

A data augmentations library for audio, image, text, and video.
Python
4,739
star
33

Kats

Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristics, detecting change points and anomalies, to forecasting future trends.
Python
4,387
star
34

DrQA

Reading Wikipedia to Answer Open-Domain Questions
Python
4,374
star
35

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.
Python
4,191
star
36

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
Python
4,035
star
37

StarSpace

Learning embeddings for classification, retrieval and ranking.
C++
3,856
star
38

fairseq-lua

Facebook AI Research Sequence-to-Sequence Toolkit
Lua
3,765
star
39

nevergrad

A Python toolbox for performing gradient-free optimization
Python
3,446
star
40

deit

Official DeiT repository
Python
3,425
star
41

dlrm

An implementation of a deep learning recommendation model (DLRM)
Python
3,417
star
42

ReAgent

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
Python
3,395
star
43

LASER

Language-Agnostic SEntence Representations
Python
3,308
star
44

VideoPose3D

Efficient 3D human pose estimation in video using 2D keypoint trajectories
Python
3,294
star
45

PyTorch-BigGraph

Generate embeddings from large-scale graph-structured data.
Python
3,238
star
46

deepmask

Torch implementation of DeepMask and SharpMask
Lua
3,113
star
47

MUSE

A library for Multilingual Unsupervised or Supervised word Embeddings
Python
3,094
star
48

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
Jupyter Notebook
3,038
star
49

pytorchvideo

A deep learning library for video understanding research.
Python
2,885
star
50

XLM

PyTorch original implementation of Cross-lingual Language Model Pretraining.
Python
2,763
star
51

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
Python
2,670
star
52

audio2photoreal

Code and dataset for photorealistic Codec Avatars driven from audio
Python
2,629
star
53

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.
Python
2,565
star
54

co-tracker

CoTracker is a model for tracking any point (pixel) on a video.
Jupyter Notebook
2,564
star
55

habitat-sim

A flexible, high-performance 3D simulator for Embodied AI research.
C++
2,521
star
56

hiplot

HiPlot makes understanding high dimensional data easy
TypeScript
2,481
star
57

fairscale

PyTorch extensions for high performance and large scale training.
Python
2,319
star
58

encodec

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
Python
2,313
star
59

InferSent

InferSent sentence embeddings
Jupyter Notebook
2,264
star
60

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
Python
2,193
star
61

pyrobot

PyRobot: An Open Source Robotics Research Platform
Python
2,109
star
62

darkforestGo

DarkForest, the Facebook Go engine.
C
2,108
star
63

ELF

An End-To-End, Lightweight and Flexible Platform for Game Research
C++
2,089
star
64

pycls

Codebase for Image Classification Research, written in PyTorch.
Python
2,053
star
65

esm

Evolutionary Scale Modeling (esm): Pretrained language models for proteins
Python
2,026
star
66

frankmocap

A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
Python
1,972
star
67

video-nonlocal-net

Non-local Neural Networks for Video Classification
Python
1,931
star
68

SentEval

A python tool for evaluating the quality of sentence embeddings.
Python
1,930
star
69

habitat-lab

A modular high-level library to train embodied AI agents across a variety of tasks and environments.
Python
1,867
star
70

ResNeXt

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks
Lua
1,863
star
71

SparseConvNet

Submanifold sparse convolutional networks
C++
1,847
star
72

swav

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882
Python
1,790
star
73

TensorComprehensions

A domain specific language to express machine learning workloads.
C++
1,747
star
74

schedule_free

Schedule-Free Optimization in PyTorch
Python
1,716
star
75

Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
Python
1,638
star
76

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.
Python
1,623
star
77

TransCoder

Public release of the TransCoder research project https://arxiv.org/pdf/2006.03511.pdf
Python
1,611
star
78

chameleon

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
Python
1,589
star
79

poincare-embeddings

PyTorch implementation of the NIPS-17 paper "PoincarΓ© Embeddings for Learning Hierarchical Representations"
Python
1,587
star
80

votenet

Deep Hough Voting for 3D Object Detection in Point Clouds
Python
1,563
star
81

pytorch_GAN_zoo

A mix of GAN implementations including progressive growing
Python
1,554
star
82

ClassyVision

An end-to-end PyTorch framework for image and video classification
Python
1,552
star
83

deepcluster

Deep Clustering for Unsupervised Learning of Visual Features
Python
1,544
star
84

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
Python
1,524
star
85

UnsupervisedMT

Phrase-Based & Neural Unsupervised Machine Translation
Python
1,496
star
86

consistent_depth

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
Python
1,479
star
87

ConvNeXt-V2

Code release for ConvNeXt V2 model
Python
1,454
star
88

Detic

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
Python
1,446
star
89

end-to-end-negotiator

Deal or No Deal? End-to-End Learning for Negotiation Dialogues
Python
1,368
star
90

DomainBed

DomainBed is a suite to test domain generalization algorithms
Python
1,355
star
91

multipathnet

A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)
Lua
1,349
star
92

CommAI-env

A platform for developing AI systems as described in A Roadmap towards Machine Intelligence - http://arxiv.org/abs/1511.08130
1,324
star
93

theseus

A library for differentiable nonlinear optimization
Python
1,306
star
94

DPR

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
Python
1,292
star
95

CrypTen

A framework for Privacy Preserving Machine Learning
Python
1,283
star
96

denoiser

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.
Python
1,272
star
97

DeepSDF

Learning Continuous Signed Distance Functions for Shape Representation
Python
1,191
star
98

TimeSformer

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
Python
1,172
star
99

House3D

a Realistic and Rich 3D Environment
C++
1,167
star
100

MaskFormer

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)
Python
1,149
star