Skip to content
@facebookresearch

Meta Research

Popular repositories

  1. llama llama Public

    Inference code for LLaMA models

    Python 47.9k 8.2k

  2. segment-anything segment-anything Public

    The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

    Jupyter Notebook 41.3k 4.8k

  3. fairseq fairseq Public

    Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

    Python 28.4k 6.3k

  4. detectron2 detectron2 Public

    Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

    Python 27.7k 7.2k

  5. faiss faiss Public

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

    C++ 26.1k 3.3k

  6. Detectron Detectron Public archive

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

    Python 26.1k 5.6k

Repositories

Showing 10 of 938 repositories
  • faiss Public

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

    C++ 26,106 MIT 3,261 388 (51 issues need help) 30 Updated Jan 5, 2024
  • GST_colorbook Public

    Geometry style transfer colorbook

    Jupyter Notebook 2 0 0 0 Updated Jan 5, 2024
  • nccl Public

    Optimized primitives for collective multi-GPU communication

    C++ 8 681 0 4 Updated Jan 5, 2024
  • spot-sim2real Public

    Spot Sim2Real Infrastructure

    Python 42 MIT 2 25 13 Updated Jan 5, 2024
  • acs Public

    Meta’s Anonymous Credential Service (ACS) is designed to enable it to authenticate users in a “de-identified manner,” permitting access to services without gathering any data that could be used to identify the subject’s identity.

    C 63 MIT 5 1 1 Updated Jan 5, 2024
  • co-tracker Public

    CoTracker is a model for tracking any point (pixel) on a video.

    Jupyter Notebook 2,085 134 16 1 Updated Jan 5, 2024
  • fbpcs Public

    FBPCS (Facebook Private Computation Solutions) leverages secure multi-party computation (MPC) to output aggregated data without making unencrypted, readable data available to the other party or any third parties. Facebook provides impression & opportunity data, and the advertiser provides conversion / outcome data.

    Python 130 MIT 156 0 96 Updated Jan 5, 2024
  • habitat-lab Public

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

    Python 1,528 MIT 431 154 (6 issues need help) 103 Updated Jan 5, 2024
  • fmmax Public

    Fourier modal method with Jax

    Python 56 MIT 2 17 (4 issues need help) 0 Updated Jan 5, 2024
  • fairseq2 Public

    FAIR Sequence Modeling Toolkit 2

    Python 494 MIT 38 13 4 Updated Jan 4, 2024
View all repositories