Bonnie404

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

kompute

General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.

EgoHOS

Fine-Grained Egocentric Hand-Object Segmentation, ECCV 2022

HANDS2022_Obj_Pose

cv-ml-lecture-notebooks

Computer Vision and Machine Learning Jupyter Notebooks for Educational Purposes

xtts-webui

Webui for using XTTS and for finetuning it

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

projectaria_tools

projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data

wgpu_playground

dpoint

Open-source digital stylus using camera tracking and inertial measurements

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

spaces

The Spaces SDK enables you build collaborative spaces for your application and enable features like Avatar stack, Live cursors, Member location, Component locking and more.

Awesome-Open-Vocabulary

(TPAMI 2024) A Survey on Open Vocabulary Learning

supervision

We write your reusable computer vision tools. 💜

PARQ

Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection (ICCV23)

candle

Minimalist ML framework for Rust

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

wonnx

A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web

gloo

A modular toolkit for building fast, reliable Web applications and libraries with Rust and WASM

web-llm

High-performance In-browser LLM Inference Engine

3DObjectTracking

Algorithms and Publications on 3D Object Tracking

nutsh

A Platform for Visual Learning from Human Feedback

makepad

Makepad is a creative software development platform for Rust that compiles to wasm/webGL, osx/metal, windows/dx11 linux/opengl

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

tldraw

SDK for creating whiteboards and canvas experiences on the web.

Co-DETR

[ICCV 2023] DETRs with Collaborative Hybrid Assignments Training

InternImage

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

font

The home for our Cal Sans font.

SpacetimeDB

Multiplayer at the speed of light

libre-caslon-condensed

An open-source condensed serif font family derived from the beloved Libre Caslon.