Repositories
-
CompilerGym
A reinforcement learning toolkit for compiler optimizations
-
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 ar…
-
faiss
A library for efficient similarity search and clustering of dense vectors.
-
vissl
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
-
mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
-
DLRM-FlexFlow
Development repository for integrating FlexFlow (A distributed deep learning framework that supports flexible parallelization strategies) with DLRM (Deep Learning Recommendation Model)
-
habitat-lab
A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.
-
nevergrad
A Python toolbox for performing gradient-free optimization
-
fbpcf
Private computation framework library allows developers to perform randomized controlled trials, without leaking information about who participated or what action an individual took. It uses secure multiparty computation to guarantee this privacy. It is suitable for conducting A/B testing, or measuring advertising lift and learning the aggregate…
-
droidlet
A modular embodied agent architecture and platform for building embodied agents
-
soundspaces-challenge
Starter code for SoundSpaces challenge at CVPR 21's Embodied AI workshop
-
habitat-sim
A flexible, high-performance 3D simulator for Embodied AI research.
-
fvcore
Collection of common code that's shared among different research projects in FAIR computer vision team.
-
pytext
A natural language modeling framework based on PyTorch
-
fews
Experiment code to create the dataset presented in the EACL2021 paper "FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary".
-
SparseConvNet
Submanifold sparse convolutional networks
-
flashlight
A C++ standalone library for machine learning
-
fairscale
PyTorch extensions for high performance and large scale training.
-
iopath
A python library that provides common I/O interface across different storage backends.
-
detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
-
ParlAI
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
-
hydra
Hydra is a framework for elegantly configuring complex applications
-
madgrad
MADGRAD Optimization Method
-
Mephisto
A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use
-
dachshund
Dachshund is a graph mining library written in Rust. It provides high performance data structures for multiple kinds of graphs, from simple undirected graphs to typed hypergraphs. Dachshund also provides algorithms for common tasks for graph mining and analysis, ranging from shortest paths to graph spectral analysis.
-
multihop_dense_retrieval
Multi-hop dense retrieval for question answering
-
habitat-challenge
Code for the habitat challenge
-
FBTT-Embedding
This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation …
-
luckmatters
Understanding Training Dynamics of Deep ReLU Networks
-
esm
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
