All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Open-source dev tools for enterprise SSO. Ship SAML + SCIM support this afternoon.

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

[ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting

A batched offline inference oriented version of segment-anything

A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment

Official Jax Implementation of MaskGIT

Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation

Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion

Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception

(T-IV, ITSC) Auto-labeling of point cloud sequences for 3D object detection using an ensemble of experts and temporal refinement

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

CLUI is a collection of JavaScript libraries for building command-driven interfaces with context-aware autocomplete.

Open3D: A Modern Library for 3D Data Processing

Open Source, Google Zanzibar-inspired database for scalably storing and querying fine-grained authorization data

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

The official Python client for the Hugging Face Hub.

This repository contains implementations and illustrative code to accompany DeepMind publications

An advanced Twitter scraping & OSINT tool written in Python that doesn't use Twitter's API, allowing you to scrape a user's followers, following, Tweets and more while evading most API limitations.

An open-source JavaScript library for world-class 3D globes and maps 🌎

Generate images from texts. In Russian

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

[ICCVW'21 Best Paper Award] All you need are a few pixels: semantic segmentation with PixelPick

Toolkit of BDD100K Dataset for Heterogeneous Multitask Learning - CVPR 2020 Oral Paper

Open source code for AlphaFold 2.

An image labelling tool for creating segmentation data sets, for Django and Flask.

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.

A web-based document annotation tool, powered by GPT-4 🚀

A python library for self-supervised learning on images.

🚀 Glide Data Grid is a no compromise, outrageously fast react data grid with rich rendering, first class accessibility, and full TypeScript support.