357 open source projects by facebookresearch

Non-local Neural Networks for Video Classification

Code for paper <PointContrast: Unsupervised Pretraining for 3D Point Cloud Understanding>

Symbol-to-Instrument Neural Generator

Official implementation of the Averaged Gradient Episodic Memory (A-GEM) in Tensorflow

PyTorch implementation of Barlow Twins.

A domain specific language to express machine learning workloads.

Fashion++: Minimal Edits for Outfit Improvement

We release dataset collected for our research, code that implement neural network models described in the paper, and scripts to reproduce all of our results, and visualization tool for visualize dataset.

visualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)

Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.

Codebase for paper "N-Bref A High-fidelity Decompiler Exploiting Programming Structures"

A Corpus for Multilingual Document Classification in Eight Languages.

A Dataset for Grounded Video Description

Supervised Multimodal Bitransformers for Classifying Images and Text

COVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations

A python tool for evaluating the quality of sentence embeddings.

Codebase for Image Classification Research, written in PyTorch.

Official DeiT repository

Equi-normalization of Neural Networks

An asynchronous RL platform for congestion control in QUIC transport protocol. https://arxiv.org/abs/1910.04054.

Stochastic Gradient Push for Distributed Deep Learning

A C++ standalone library for machine learning

Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

Phrase-Based & Neural Unsupervised Machine Translation

Visual Relationship Detection

Research code implementing the search AI agent for Hanabi, as well as a web server so people can play against it

Open source repository for the code accompanying the paper 'Non-Rigid Neural Radiance Fields Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video'.

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

Learning Temporal Pose Estimation from Sparsely Labeled Videos

PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection

Hierarchical Visibility for Virtual Reality, which implements a hybrid CPU/GPU ray-caster, suited for real time rendering of effects such as lens distortion.

This repository provides code for reproducing experiments of the paper Talk The Walk: Navigating New York City Through Grounded Dialogue by Harm de Vries, Kurt Shuster, Dhruv Batra, Devi Parikh, Jason Weston, and Douwe Kiela.

Learning to align and match videos with kernelized temporal layers

Submanifold sparse convolutional networks

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

With the aim of building next generation virtual assistants that can handle multimodal inputs and perform multimodal actions, we introduce two new datasets (both in the virtual shopping domain), the annotation schema, the core technical tasks, and the baseline models. The code for the baselines and the datasets will be opensourced.

code for paper "Graph Structure of Neural Networks"

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

We are implementing differentiable models of robot manipulators, which allows us to learn typically assumed to be known models of robots for control and motion planning. These models can then be used in more complex reinforcement learning settings, hopefully making learning more sample-efficient. Furthermore, such differentiable models can also be used for learning simulators.

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 is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

evaluation dataset consisting of natural language query and code snippet pairs

A first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.

Deal or No Deal? End-to-End Learning for Negotiation Dialogues

Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees

A code implementation for our arXiv paper "Multi-agent Adhoc Team Play using Decompositional Q function"

Library for converting clinical trial eligibility criteria to a machine-readable format.

CoDraw dataset

A mix of GAN implementations including progressive growing

Implementations of quasi-hyperbolic optimization algorithms.