357 open source projects by facebookresearch

End-to-End Object Detection with Transformers

A natural language modeling framework based on PyTorch

Inferring and Executing Programs for Visual Reasoning

Fader Networks: Manipulating Images by Sliding Attributes - NIPS 2017

A framework for Privacy Preserving Machine Learning

We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

mixup: Beyond Empirical Risk Minimization

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

LAnguage Model Analysis

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

Facebook AI Research's Automatic Speech Recognition Toolkit

Collection of common code that's shared among different research projects in FAIR computer vision team.

Learning Continuous Signed Distance Functions for Shape Representation

ImageNet classifier with state-of-the-art adversarial robustness

Code for: "And the bit goes down: Revisiting the quantization of neural networks"

A large-scale dataset of both raw MRI measurements and clinical MRI images

A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.

Proposes neural networks that can generate animation of virtual characters for different actions.

Mobile vision models and code

Entity Linker solution

A virtual assistant bot in Minecraft

Transformer training code for sequential tasks

Weakly Supervised Learning On Images

Library for fast text representation and classification.

Scaling and Benchmarking Self-Supervised Visual Representation Learning

Code for using and evaluating SpanBERT.

Code for paper

Recipe Generation from Food Images

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 2020

A PyTorch Platform for Distributed RL

The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

View synthesis for the public.

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Library for Knowledge Intensive Language Tasks

Multi Task Vision and Language

D2Go is a toolkit for efficient deep learning

Reading Wikipedia to Answer Open-Domain Questions

Hydra is a framework for elegantly configuring complex applications

Automatic differentiation with weighted finite-state transducers.

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.

A repository in preparation for open-sourcing lottery ticket hypothesis code.

This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic parsing. TaBERT is pre-trained on a massive corpus of 26M Web tables and their associated natural language context, and could be used as a drop-in replacement of a semantic parsers original encoder to compute representations for utterances and table schemas (columns).

A UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.

Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)

The NetHack Learning Environment

Facebook AI Research Sequence-to-Sequence Toolkit

PHYRE is a benchmark for physical reasoning.