OpenMMLab
lastmod 2026-11-10created 2021-10-203 edits
OpenMMLab is a collection of PyTorch-based open-source computer vision projects. Its per-domain toolboxes for object detection, segmentation, pose estimation, action recognition, and more are built on common foundation libraries called MMCV and MMEngine. They share an approach of defining models and the training process in config files; this page collects the sub-project entries.
Categories
- MMEngine
- MMClassification - OpenMMLab image classification toolbox and benchmark.
- MMDetection - OpenMMLab detection toolbox and benchmark.
- MMDetection3D - OpenMMLab's next-generation platform for general 3D object detection.
- MMSegmentation - OpenMMLab semantic segmentation toolbox and benchmark.
- MMAction2 - OpenMMLab's next-generation action understanding toolbox and benchmark.
- MMTracking - OpenMMLab video perception toolbox and benchmark.
- MMPose - OpenMMLab pose estimation toolbox and benchmark.
- MMEditing - OpenMMLab image and video editing toolbox.
- MMOCR - OpenMMLab text detection, recognition and understanding toolbox.
- MMGeneration - OpenMMLab image and video generative models toolbox.
- MMCV - OpenMMLab Computer Vision Foundation
- MIM - MIM Installs OpenMMLab Packages