MMDetection is an open source object detection toolbox that's part of the OpenMMLab project developed by Multimedia Laboratory, CUHK. It stems from the codebase developed by the MMDet team, who won the COCO Detection Challenge in 2018. Since that win this toolbox has continuously been developed and improved.
MMDetection detects various objects within a given image with high efficiency. Its training speed is comparable or even faster than those of other codebases like Detectron2 and SimpleDet. It supports multiple detection frameworks right out of the box, as well as various backbones and methods.
Features
- Modular Design
- Readily supports multiple frameworks
- Fast and highly efficient
- Award-winning codebase
License
Apache License V2.0Other Useful Business Software
Run applications fast and securely in a fully managed environment
Run frontend and backend services, batch jobs, deploy websites and applications, and queue processing workloads without the need to manage infrastructure.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of MMDetection!