Lists (1)
Starred repositories
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Flutter makes it easy and fast to build beautiful apps for mobile and beyond
A Flutter plugin for controlling hardware-level features on Rockchip RK series boards (e.g. RK3288, RK3399, RK3568).
detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.
Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).
an empirical study on few-shot counting using segment anything (SAM)
This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point or box annotation.
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.
Displays a highly customizable week view (or day view) which is able to display events, to be scrolled, to be zoomed-in & out and a lot more !
收录独立开发、AI出海领域最新、最实用的工具与资源（Build Faster with Better Tools）
FastAPI SAAS Template (Boilerplate code)
In this project, I'm developing an image classifier to determine if an image is AI-generated or real. I'm currently using EfficientNetB4 for training and have built the application with Flask for …
This project is a Convolutional Neural Network (CNN)-based binary image classification model built using TensorFlow/Keras. It classifies images as either real or fake, using a dataset of labeled tr…
Deepfake Image Detection using Convolutional Neural Networks (CNN) with PyTorch and TensorFlow, achieving ~97% accuracy. Classifies real and fake images with efficient preprocessing and model train…
An attempt to detect AI generated images in a generalized manner.
EasyDisplay is designed for easy content management and reliable display on various screens. For usage details and updates, please see the README.
快图设计-基于fabric.js和Vue的开源图片编辑器，可自定义字体、素材、设计模板。fabric.js and Vue based image editor, can customize fonts, materials, design templates.
A curated list of digital signage software.
An open source project which helps you to create a curved bottom navigation.
Vue 用于可调整大小和可拖动元素的组件并支持冲突检测、元素吸附、元素对齐、辅助线
开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.