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.

Google Research

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Draw pretty maps from OpenStreetMap data! Built with osmnx +matplotlib + shapely

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

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

CoreNet: A library for training deep neural networks

A Bulletproof Way to Generate Structured JSON from Language Models

Data augmentation for NLP

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Text and code for the second edition of Think Bayes, by Allen Downey.

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

Fast, general, and tested differentiable structured prediction in PyTorch

An introduction to network analysis and applied graph theory using Python and NetworkX

3D mesh stylization driven by a text input in PyTorch

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

[DEIMv2] Real Time Object Detection Meets DINOv3

Tutorials and content created by Earth Engine users, for Earth Engine users

Notebooks for the third edition of Think Stats

Graph Data Science: an abstraction layer in Python for building knowledge graphs, integrated with popular graph libraries – atop Pandas, NetworkX, RAPIDS, RDFlib, pySHACL, PyVis, morph-kgc, pslpyth…

OpenL3: Open-source deep audio and image embeddings

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

A python wrapper to extract text from images on a mac system. Uses the vision framework from Apple.

This Python library makes it easy to display images and videos in a notebook.

Broccoli - distributed task queues for ESP32 cluster

Additive manufacturing simulation with JAX.

Interactive ChipWhisperer tutorials using Jupyter notebooks.

OneShot Learning-based hotword detection.

The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"