llamaInference code for LLaMA models
segment-anythingThe 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.
DetectronFAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
fairseqFacebook AI Research Sequence-to-Sequence Toolkit written in Python.
detectron2Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
fastTextLibrary for fast text representation and classification.
faissA library for efficient similarity search and clustering of dense vectors.
audiocraftAudiocraft 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.
detrEnd-to-End Object Detection with Transformers
codellamaInference code for CodeLlama models
ParlAIA framework for training and evaluating AI models on a variety of openly available dialogue datasets.
maskrcnn-benchmarkFast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
pifuhdHigh-Resolution 3D Human Digitization from A Single Image.
AnimatedDrawingsCode to accompany "A Method for Animating Children's Drawings of the Human Figure"
ImageBindImageBind One Embedding Space to Bind Them All
pytorch3dPyTorch3D is FAIR's library of reusable components for deep learning with 3D data
hydraHydra is a framework for elegantly configuring complex applications
nougatImplementation of Nougat Neural Optical Understanding for Academic Documents
dinov2PyTorch code and models for the DINOv2 self-supervised learning method.
DensePoseA real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
pytextA natural language modeling framework based on PyTorch
metaseqRepo for external large-scale work
demucsCode for the paper Hybrid Spectrogram and Waveform Source Separation
seamless_communicationFoundational Models for State-of-the-Art Speech and Text Translation
SlowFastPySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
maePyTorch implementation of MAE https//arxiv.org/abs/2111.06377
mmfA modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
llama-recipesExamples and recipes for Llama 2 model
ConvNeXtCode release for ConvNeXt model
dinoPyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
AugLyA data augmentations library for audio, image, text, and video.
KatsKats, 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.
DrQAReading Wikipedia to Answer Open-Domain Questions
xformersHackable and optimized Transformers building blocks, supporting a composable construction.
mocoPyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
StarSpaceLearning embeddings for classification, retrieval and ranking.
fairseq-luaFacebook AI Research Sequence-to-Sequence Toolkit
nevergradA Python toolbox for performing gradient-free optimization
deitOfficial DeiT repository
dlrmAn implementation of a deep learning recommendation model (DLRM)
ReAgentA platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
LASERLanguage-Agnostic SEntence Representations
VideoPose3DEfficient 3D human pose estimation in video using 2D keypoint trajectories
PyTorch-BigGraphGenerate embeddings from large-scale graph-structured data.
deepmaskTorch implementation of DeepMask and SharpMask
MUSEA library for Multilingual Unsupervised or Supervised word Embeddings
visslVISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
pytorchvideoA deep learning library for video understanding research.
XLMPyTorch original implementation of Cross-lingual Language Model Pretraining.
hiplotHiPlot makes understanding high dimensional data easy
fairscalePyTorch extensions for high performance and large scale training.
encodecState-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
ijepaOfficial 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."
InferSentInferSent sentence embeddings
pyrobotPyRobot: An Open Source Robotics Research Platform
darkforestGoDarkForest, the Facebook Go engine.
ELFAn End-To-End, Lightweight and Flexible Platform for Game Research
pyclsCodebase for Image Classification Research, written in PyTorch.
esmEvolutionary Scale Modeling (esm): Pretrained language models for proteins
frankmocapA Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
habitat-simA flexible, high-performance 3D simulator for Embodied AI research.
co-trackerCoTracker is a model for tracking any point (pixel) on a video.
video-nonlocal-netNon-local Neural Networks for Video Classification
SentEvalA python tool for evaluating the quality of sentence embeddings.
ResNeXtImplementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks
SparseConvNetSubmanifold sparse convolutional networks
swavPyTorch implementation of SwAV https//arxiv.org/abs/2006.09882
TensorComprehensionsA domain specific language to express machine learning workloads.
Mask2FormerCode release for "Masked-attention Mask Transformer for Universal Image Segmentation"
fvcoreCollection of common code that's shared among different research projects in FAIR computer vision team.
TransCoderPublic release of the TransCoder research project https://arxiv.org/pdf/2006.03511.pdf
poincare-embeddingsPyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
votenetDeep Hough Voting for 3D Object Detection in Point Clouds
pytorch_GAN_zooA mix of GAN implementations including progressive growing
ClassyVisionAn end-to-end PyTorch framework for image and video classification
deepclusterDeep Clustering for Unsupervised Learning of Visual Features
higherhigher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
UnsupervisedMTPhrase-Based & Neural Unsupervised Machine Translation
consistent_depthWe estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
habitat-labA modular high-level library to train embodied AI agents across a variety of tasks and environments.
DeticCode release for "Detecting Twenty-thousand Classes using Image-level Supervision".
DiTOfficial PyTorch Implementation of "Scalable Diffusion Models with Transformers"
end-to-end-negotiatorDeal or No Deal? End-to-End Learning for Negotiation Dialogues
multipathnetA Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)
CommAI-envA platform for developing AI systems as described in A Roadmap towards Machine Intelligence - http://arxiv.org/abs/1511.08130
theseusA library for differentiable nonlinear optimization
DPRDense Passage Retriever - is a set of tools and models for open domain Q&A task.
CrypTenA framework for Privacy Preserving Machine Learning
denoiserReal 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.
DeepSDFLearning Continuous Signed Distance Functions for Shape Representation
TimeSformerThe official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
House3Da Realistic and Rich 3D Environment
ConvNeXt-V2Code release for ConvNeXt V2 model
MaskFormerPer-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)
LAMALAnguage Model Analysis
fastMRIA large-scale dataset of both raw MRI measurements and clinical MRI images.
meshrcnncode for Mesh R-CNN, ICCV 2019
mixup-cifar10mixup: Beyond Empirical Risk Minimization
DomainBedDomainBed is a suite to test domain generalization algorithms
BLINKEntity Linker solution