CVHub

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

A desktop tool for labeling images and videos with AI assistance, letting you train machine learning models by marking objects in images far faster than doing it by hand.

A Simple, Lightweight, and Extensible Serving Framework for X-AnyLabeling

No description.

No description.

This project showcases the deployment of the RT-DETR model using ONNXRUNTIME in C++ and Python.

EfficientViT is a new family of vision models for efficient high-resolution vision.

The repository provides code for running image, video, and camera inference using the SAM 2.

No description.

This project showcases the deployment of the encoder and decoder model using ONNXRUNTIME in Python.

No description.

Official implementation of SAM-Med2D

A repository that brings together a variety of readily usable deep learning modules, including convolution, attention, feature fusion, and more, to help you quickly build your deep learning models.

No description.