Giters
Meta Research (facebookresearch)

Meta Research

facebookresearch

Geek Repo

Location:Menlo Park, California

Home Page:https://opensource.fb.com

Github PK Tool:Github PK Tool

Meta Research's repositories

Detectron

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

Language:PythonLicense:Apache-2.0Stargazers:26178Issues:943Issues:925

pifuhd

High-Resolution 3D Human Digitization from A Single Image.

Language:PythonLicense:NOASSERTIONStargazers:9446Issues:271Issues:180

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

Language:PythonLicense:MITStargazers:8309Issues:69Issues:192

PyTorch-BigGraph

Generate embeddings from large-scale graph-structured data.

Language:PythonLicense:NOASSERTIONStargazers:3354Issues:90Issues:196

encodec

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

Language:PythonLicense:MITStargazers:3255Issues:57Issues:70

DomainBed

DomainBed is a suite to test domain generalization algorithms

Language:PythonLicense:MITStargazers:1340Issues:32Issues:102

svoice

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.

Language:PythonLicense:NOASSERTIONStargazers:1174Issues:25Issues:88

localrf

An algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video.

Language:PythonLicense:MITStargazers:951Issues:18Issues:45

flores

Facebook Low Resource (FLoRes) MT Benchmark

Language:PythonLicense:NOASSERTIONStargazers:663Issues:66Issues:44

NeuralCompression

A collection of tools for neural compression enthusiasts.

Language:PythonLicense:MITStargazers:477Issues:22Issues:69

OrienterNet

Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"

Language:PythonLicense:NOASSERTIONStargazers:421Issues:10Issues:42

belebele

Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.

Language:PythonLicense:NOASSERTIONStargazers:304Issues:5Issues:8

DistDepth

Repository for "Toward Practical Monocular Indoor Depth Estimation" (CVPR 2022)

Language:PythonLicense:NOASSERTIONStargazers:214Issues:10Issues:30

Ad-Library-API-Script-Repository

GitHub repository of commonly used python scripts that allows everyone to pull data via the Ad Library API

Language:PythonLicense:NOASSERTIONStargazers:204Issues:37Issues:33

robust-dynrf

An algorithm for reconstructing the radiance field of a dynamic scene from a casually-captured video.

Language:PythonLicense:MITStargazers:202Issues:8Issues:27

ResponsibleNLP

Repository for research in the field of Responsible NLP at Meta.

Language:PythonLicense:NOASSERTIONStargazers:165Issues:22Issues:5

motif

Intrinsic Motivation from Artificial Intelligence Feedback

Language:PythonLicense:NOASSERTIONStargazers:112Issues:7Issues:3

Generic-Grouping

Open-source code for Generic Grouping Network (GGN, CVPR 2022)

Language:PythonLicense:NOASSERTIONStargazers:111Issues:8Issues:12

DVSR

DVSR ("Consistent Direct Time-of-Flight Video Depth Super-Resolution"), CVPR 2023

Language:PythonLicense:NOASSERTIONStargazers:91Issues:7Issues:7

assemblyhands-toolkit

AssemblyHands Toolkit is a Python package that provides data loader, visualization, and evaluation tools for the AssemblyHands dataset (CVPR 2023).

Language:PythonLicense:NOASSERTIONStargazers:87Issues:13Issues:19

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.

Language:RustLicense:MITStargazers:85Issues:17Issues:7

NGDF

Neural Grasp Distance Fields for Robot Manipulation

Language:PythonLicense:MITStargazers:73Issues:7Issues:16

jps

Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"

Language:C++License:NOASSERTIONStargazers:48Issues:7Issues:2

three_bricks

Official Implementation of the paper "Three Bricks to Consolidate Watermarks for LLMs"

Language:PythonLicense:NOASSERTIONStargazers:35Issues:1Issues:3

grounding-inductive-biases

reproduces experiments from "Grounding inductive biases in natural images: invariance stems from variations in data"

Language:PythonLicense:NOASSERTIONStargazers:16Issues:19Issues:0

RidgeSketch

A Fast sketching based solver for large scale ridge regression

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:16Issues:7Issues:1

dual-system-for-visual-language-reasoning

Github repo for Peifeng's internship project

Language:PythonLicense:NOASSERTIONStargazers:11Issues:1Issues:2

video_rep_learning

SSL Video Representation Learning project

Language:PythonLicense:NOASSERTIONStargazers:10Issues:4Issues:0

PerSE

Personalized Story Evaluation Model

Language:PythonLicense:NOASSERTIONStargazers:6Issues:0Issues:0

LDCT-VAM

Local-dose-controlled tomographic VAM (LDCT-VAM) is a fork of VAMToolbox with additional functionalities to support control of local material conversion.

Language:PythonLicense:NOASSERTIONStargazers:3Issues:2Issues:0