✨✨Latest Advances on Multimodal Large Language Models

A collaboration friendly studio for NeRFs

LlamaIndex is a data framework for your LLM applications

Machine Learning Engineering Open Book

Industry leading face manipulation platform

Python packaging and dependency management made easy

PixelLM is an effective and efficient LMM for pixel-level reasoning and understanding. PixelLM is accepted by CVPR 2024.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Focus on prompting and generating

Code for "Object as Query: Lifting any 2D Object Detector to 3D Detection"

ReBound is an open-source, LiDAR visualization and annotation tool to assist active-learning systems involved in autonomous vehicles

An Open Source Lemon Squeezy alternative with better pricing! Get paid coding on your passion.

Stable Diffusion web UI

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT3.5/GPT-4o/GPT-o1/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

Google Drive Public File Downloader when Curl/Wget Fails

High-Resolution Image Synthesis with Latent Diffusion Models

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

Awesome 3D Computer Vision and Computer Graphics.

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275 supported cars.

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

(CGCSTCD'2017) An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations. CGCSTCD = China Graduate Contest on Smart-city Technology and Creative Design

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Anomaly detection related books, papers, videos, and toolboxes

Ready-to-use OCR with 80 supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

The service for the demonstration of transforms in Albumentations library