OpenModal is a foundational library for training multi-modal models based on PyTorch

code for paper: Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning

SemiSupervisedObjectDetection

using two consistent images(aerial image) with gps to build the piex2gps formula, which could be used to get the gps of all piexes using SIFT algorithm

diseased_pinewood_detection by FRCNN and DETR

code for paper: Hot Topic Clustering based on Gaussian Mixture Model with built-in DTW

本项目开源基于NextJS的前端， 希望能够提供一个用于生成式AI的文字转视频， 尤其是电影从编剧到视频生成的Web前端平台参考。Everyone can become a director. The Nextjs front-end of an AI driven platform for automatic movie/video generation (form GPT script …

利用opencv实现PDF文件自定义化去水印功能，利用ocr实现PDF文字提取功能

The application of large pre-trained vision model DINOv2 from MetaAI for feature points matching, and a ViT decoder used for Auto Encoder

code for paper: E-commerce Platform Intellectual Property Monitoring System Based on Algorithm Engine and Big Data Technology

face-monitoring-raspberry-pi

Motion Ball Grasping Robot and Medicine Box Sorting Robot Based on Computer Vision

Second Prize in Zhejiang Province, 2020 National College Student Mathematical Contest in Modeling

An air-plane ticket booking system bases on java awt

基于MVC开发的大富翁游戏，前后端分离架构

Some basic practices for the beginers of Opencv library

An Android application that could control the openwrt router devices