357 open source projects by facebookresearch

Generate embeddings from large-scale graph-structured data.

A library for Multilingual Unsupervised or Supervised word Embeddings

DomainBed is a suite to test domain generalization algorithms

Train embodied agents that can answer questions in environments

An implementation of a deep learning recommendation model (DLRM)

Video Grounding and Captioning

On Ends-to-Ends Encryption: Asynchronous Group Messaging with Strong Security Guarantees

Neural Text Generation with Unlikelihood Training

Training and Evaluation Code for Neural Volumes

Implements the unsupervised pre-training of convolutional neural networks

PyTorch original implementation of Cross-lingual Language Model Pretraining.

New dataset

The QMNIST dataset

Scripts and links to recreate the ELI5 dataset.

PyTorch code to run synthetic experiments.

Efficient 3D human pose estimation in video using 2D keypoint trajectories

A predictive model developed to identify medium-voltage electrical distribution grid infrastructure using publicly available data sources.

Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.

Semi-supervised ImageNet1K models

Code for "MultiGrain: a unified image embedding for classes and instances"

A library for efficient similarity search and clustering of dense vectors.

DarkForest, the Facebook Go engine.

Exploring Random Encoders for Sentence Classification

RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms. It includes a library, a tutorial, and different RL algorithms provided as examples.

InferSent sentence embeddings

CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)

EGG: Emergence of lanGuage in Games

Unsupervised Question answering via Cloze Translation

dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.

HiPlot makes understanding high dimensional data easy

Adversarial Natural Language Inference Benchmark

An End-To-End, Lightweight and Flexible Platform for Game Research

A compact C preprocessor and declaration parser written in pure Lua

Tools for state of the art Knowledge Base Completion.

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Global Reasoning module for visual recognition

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

The release codes of LA-MCTS with its application to Neural Architecture Search.

Autoregressive Entity Retrieval

PyRobot: An Open Source Robotics Research Platform

Implementation for the paper "Adversarial Continual Learning" in PyTorch.

A python to bpf (Berkeley Packet Filter bytecode) converter

Hyperbolic Graph Neural Networks

Fast Depth Densification for Occlusion-Aware Augmented Reality

Code for the habitat challenge

Facebook Low Resource (FLoRes) MT Benchmark

A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.

Grid features pre-training code for visual question answering

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks