MambaGlue: Fast and Robust Local Feature Matching With Mamba @ ICRA'25

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

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

Official code for 'DatasetDM:Synthesizing Data with Perception Annotations Using Diffusion Models'

Paint by Example: Exemplar-based Image Editing with Diffusion Models

Xtreme1 - The Next GEN Platform for Multimodal Training Data. #3D annotation, lidar-camera fusion annotation, image annotation and visualation tools are supported!

A lightweight tool for labeling 3D bounding boxes in point clouds.

FastPillars: A Deployment-friendly Pillar-based 3D Detector

The simplest, fastest repository for training/finetuning medium-sized GPTs.

3D Point Cloud Annotation Platform for Autonomous Driving

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

Chinese version of GPT2 training code, using BERT tokenizer.

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

YOLOv3、YOLOv4、YOLOv5、YOLOv5-Lite、YOLOv6、YOLOv7、YOLOX、YOLOX-Lite

Gluon CV Toolkit

这是一个yolov7的库，可以用于训练自己的数据集。

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别

YOLOv6: a single-stage object detection framework dedicated to industrial application.

An unofficial implementation of Pytorch version PP-YOLOE,based on Megvii YOLOX training code.

Demo and other Python3 code

A PyTorch version of You Only Look at One-level Feature object detector

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

C++ library based on tensorrt integration

OpenMMLab Model Compression Toolbox and Benchmark.

deep learning for image processing including classification and object-detection etc.

软件注册及授权

improvement research based on YOLOV5,SwintransformV2 and attention op. training skills, business customization, engineering deployment C