Shuwei Ji

X-AnyLabeling. Effortless data labeling with AI support from Segment Anything and other awesome models.

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform

yolo11-ncnn. Use ncnn model of yolo11 without magic operation

UniRepLKNet. [CVPR 2024 & TPAMI 2025] UniRepLKNet

black. The uncompromising Python code formatter

isort. A Python utility / library to sort imports.

ISAT_with_segment_anything. Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

bullet3. Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

drawio-desktop. Official electron build of draw.io

PIV. A Particle Image Velocimetry (PIV) code in Python and Matlab

Lite-HRNet. This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.

sphinx. The Sphinx documentation generator

StomataPy. Datasets and Generalized Models for Leaf Epidermal Segmentation

rocketmq-clients. RocketMQ Clients - Collection of Client Bindings for Apache RocketMQ

akshare. AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

tablegpt-agent. A pre-built agent for TableGPT2.

dress-code. Dress Code: High-Resolution Multi-Category Virtual Try-On. ECCV 2022

HiC.

rembg. Rembg is a tool to remove images background

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

clash-verge-rev. A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

s1. s1: Simple test-time scaling

unsloth. Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Garment-Pattern-Generator. Official implementation of Generating Datasets of 3D Garments with Sewing Patterns

SMPL_maya_plugin. Maya plugin for SMPL model integration

smplx. SMPL-X

amass. Data preparation and loader for AMASS

samurai. Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

icones. ⚡️ Icon Explorer with Instant searching, powered by Iconify

ResNeSt. ResNeSt: Split-Attention Networks

sewformer. Python

Okutama-Action. Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

Efficient-AI-Backbones. Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

yolov9. Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

docker-drag. Download image from the Docker Hub HTTPS API

sam2. 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 the model.

public-apis. A collective list of free APIs

DeepFashion2. DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf

sahi. Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

Rein. [CVPR 2024] Official implement of <Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation>

rtabmap. RTAB-Map library and standalone application

mastodon. Your self-hosted, globally interconnected microblogging community

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

autogluon. Fast and Accurate ML in 3 Lines of Code

blog. Public repo for HF blog posts

deep-learning-pytorch-huggingface. Jupyter Notebook

img2img-turbo. One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

grok-1. Grok open release

qtbox. Qt Box is a handy tool in PyQt & PySide development.

streamlit-drawable-canvas. Do you like Quick, Draw? Well what if you could train/predict doodles drawn inside Streamlit? Also draws lines, circles and boxes over background images for annotation.

BackgroundRemoval. Remove background from any image

CogVLM. a state-of-the-art-level open visual language model | 多模态预训练模型

Osprey. [CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"

stable-diffusion. A latent text-to-image diffusion model

lora-scripts. SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

ComfyUI-Manager. ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.

ComfyUI_Dave_CustomNode. JavaScript

CascadePSP. [CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

python_plot_utils. A simple code for plotting figure, colorbar, and cropping with python

ultralytics. Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

GLIP. Grounded Language-Image Pre-training

rcg. PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

LaTeX-OCR. pix2tex: Using a ViT to convert images of equations into LaTeX code.

segment-anything-fast. A batched offline inference oriented version of segment-anything

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

EditAnything. Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

FastSAM. Fast Segment Anything

ChatGLM3. ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

multinerf. A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

awesome-segment-anything. Tracking and collecting papers/projects/others related to Segment Anything.

dataset. 医学影像数据集列表 『An Index for Medical Imaging Datasets』

star-history. The de facto GitHub star history graph.

GLM-130B. GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

ChatDev. ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

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

Chinese-Vicuna. Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

CodeGeeX2. CodeGeeX2: A More Powerful Multilingual Code Generation Model

awesome-chatgpt-prompts-zh. ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

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

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Langchain-Chatchat. Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

Personalize-SAM. Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

ChatGLM2-6B. ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

sam-hq. Segment Anything in High Quality [NeurIPS 2023]

SSD-Pytorch. SSD目标检测算法(Single Shot MultiBox Detector)(简单,明了,易用,全中文注释,单机多卡训练,视频检测)( If you train the model on a single computer and mutil GPU, this program will be your best choice , easier to use and easier to understand )

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

DINO. [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

Swin-Transformer-Object-Detection. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

paper-reading. 深度学习经典、新论文逐段精读

baikaixin-public.github.io. HTML

SAMLabelerPro. label your image with Segment Anything Model or MobileSAM, support remote labeling for multiple persons。使用Segment Anything Model或MobileSAM辅助标注的工具，支持多人远程标注

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

segment-anything. 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.

ISAT. ISAT - Image segmentation annotation tool.（图像分割标注工具，支持语义分割与实例分割）

mmgeneration. MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

LoFTR. Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

openpoints. OpenPoints: a library for easily reproducing point-based methods for point cloud understanding. The engine for [ASSANet](https://arxiv.org/abs/2110.10538), [PointNeXt](https://arxiv.org/abs/2206.04670)

contrastBoundary. Contrastive Boundary Learning for Point Cloud Segmentation (CVPR2022)

PointNeXt. [NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

PSAT. PSAT - Point cloud segmentation annotation tool. （点云分割标注工具，同时支持语义分割与实例分割）

DeOldify. A Deep Learning based project for colorizing and restoring old images (and video!)

SensatUrban. 🔥Urban-scale point cloud dataset (CVPR 2021 & IJCV 2022)

CSF. LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation

WebStack-Hugo. WebStack 网址导航 Hugo 主题，无需服务器，支持导航一键配置的纯静态网址导航网站。

laspy. Laspy is a pythonic interface for reading/modifying/creating .LAS LIDAR files matching specification 1.0-1.4.

SNIPER. SNIPER / AutoFocus is an efficient multi-scale object detection training / inference algorithm

Learn-OpenGL-in-python. All the source codes from my youtube tutorial series called "OpenGL in python".

battle-city. 🎮 Battle city remake built with react.

serve. Static file serving and directory listing

freeproxy. 可扩展的自动化个人代理ip池

IconPark. 🍎Transform an SVG icon into multiple themes, and generate React icons，Vue icons，svg icons

TrinityCore. TrinityCore Open Source MMO Framework (master = 12.0.7.68453, 3.3.5 = 3.3.5a.12340, cata classic = 4.4.2.60895)

UeCore. UeCore(Universe Engine Core) is an Open Source MMO RPG Framework World of Warcraft Server Engine (NOT Unreal Engine)

openMVS. open Multi-View Stereo reconstruction library

openMVG. open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

OpenMVGOpenMVS. OpenMVG+OpenMVS

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

PixelAnnotationTool. Annotate quickly images.

jetson-inference. Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

qemu-user-static. :earth_africa: `/usr/bin/qemu-*-static`

DecryptLogin. DecryptLogin: APIs for loginning some websites by using requests.

electron. :electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS

GRNet. The official implementation of "GRNet: Gridding Residual Network for Dense Point Cloud Completion". (ECCV 2020)

chineseocr. yolo3+ocr

dlib. A toolkit for making real world machine learning and data analysis applications in C++

face_recognition. The world's simplest facial recognition api for Python and the command line

mmpose. OpenMMLab Pose Estimation Toolbox and Benchmark.

MagicCube. MagicCube

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

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Motrix. A full-featured download manager.

GMS-Feature-Matcher. GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence (CVPR 17 & IJCV 20)

labelme. Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

wtfpython-cn. wtfpython的中文翻译/持续🚧.../ 能力有限，欢迎帮我改进翻译

pythonguis-examples. Build desktop apps built with Python. Examples for PyQt6, PySide6, Flet, DearPyGUI, Kivy, NiceGUI, Streamlit, Tkinter, PyQt5 & PySide2

blind_watermark. Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！

Airtest. UI Automation Framework for Games and Apps

scrcpy. Display and control your Android device

CPlusPlusThings. C++那些事

StockQuant. 股票量化

involution. [CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

Python_NetEaseMusicAPI. Python版的网易云音乐API，基于django3.0搭建

mutagen. Python module for handling audio metadata

FeTool. 一些在工作或生活中用Python写的小工具集，不稳定更新中

pip. The Python package installer

votenet. Deep Hough Voting for 3D Object Detection in Point Clouds

models. Models and examples built with TensorFlow

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

awesome-object-detection. Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

ObjectDetection-OneStageDet. 单阶段通用目标检测器

mmdetection. OpenMMLab Detection Toolbox and Benchmark

nvidia-docker. Build and run Docker containers leveraging NVIDIA GPUs

yolodet-pytorch. reproduce the YOLO series of papers in pytorch, including YOLOv4, PP-YOLO, YOLOv5，YOLOv3, etc.

github-readme-stats. :zap: Dynamically generated stats for your github readmes

jsis3d. [CVPR'19] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds

ASIS. Associatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019

leetcode-python. python刷leetcode记录。项目含有详细的代码注释和解题思路，并配有对应的leetcode中英文题目。The project contains detailed code comments and solution ideas(chinese), and has corresponding leetcode question content(Chinese and English).

home. Rime::Home is home to Rime users and developers

emoji-list. emoji list; emoji表情列表

pycls. Codebase for Image Classification Research, written in PyTorch.

README. README文件语法解读，即Github Flavored Markdown语法介绍

lux. 👾 Fast and simple video download library and CLI tool written in Go

bbs-go. A lightweight community and Q&A platform for forums, knowledge bases, and discussions.一个轻量级社区和问答平台。

blog. 个人博客

spikeSystem. 一个秒杀系统的例子分析

TopList. 今日热榜，一个获取各大热门网站热门头条的聚合网站，使用Go语言编写，多协程异步快速抓取信息，预览:https://mo.fish

simple-computer. the scott CPU from "But How Do It Know?" by J. Clark Scott

gochat. goim server write by golang !🚀

netron. Visualizer for neural network, deep learning and machine learning models

practical-python. Practical Python Programming (course by @dabeaz)

GeneralNewsExtractor. 新闻网页正文通用抽取器 Beta 版.

KPConv-PyTorch. Kernel Point Convolution implemented in PyTorch

Pointnet2.PyTorch. A faster implementation of PointNet++ based on PyTorch.

fiora. An interesting open source chat application. Developed with node.js, mongoDB, socket.io and react

GPT2-chitchat. GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型

AutomatedTesting. 自然语言驱动的自动化测试框架

education-project. 使用jquery+echarts做的大数据可视化前端展示，喜欢的点点star和fork!

RSNet. This is the official implementation of RSNet.

DetectionUpperbound. Code for calculating the upper bound AP in object detection

chart.xkcd. xkcd styled chart lib

cutecharts.py. 📉 Hand drawing style charts library for Python

PlotNeuralNet. Latex code for making neural networks diagrams

superpoint_graph. Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

java_study. 记录java的一些学习笔记.mysql/ spring/ mybatis/ demo--- 持续更新

nsfw-resnet. 🔥🔥NSFW implement in pytorch（色情图&性感图识别，本程序经过了线上大数据集测试，性能优异效果良好）🔥🔥

high-precision-four-fundamental-rules. a npm packge of high-precision-four-fundamental-rules, which can make up for the defect of accuracy of native JS.（高精度的基本四则运算npm包，用来弥补原生JS计算精度缺失的缺陷）

OCSystem. 🚀ONLYCHAIN blockchain underlying system-OCSystem

SSD. High quality, fast, modular reference implementation of SSD in PyTorch

PySimpleGUI. Python GUIs for Humans! Create any GUI simple or complicated in a way that's intuitive. Launched in 2018. NEW for 2026 - the LGPL3 Version 6. Transforms tkinter, Qt, WxPython, and Remi into a simple, intuitive, and fun experience for both hobbyists and expert users.

pointnet2. pointnet2(点云分割, 基于pytorch,全中文注释)

Pointnet_Pointnet2_pytorch. PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

free-api. 收集免费的接口服务,做一个api的搬运工

Machine-Learning. 机器学习算法实现(python)(详细的实现过程备注以及丰富的例子)