MMTracking is an open source video perception toolbox by PyTorch. It is a part of OpenMMLab project.
It supports 4 video tasks:
- Video object detection (VID)
- Single object tracking (SOT)
- Multiple object tracking (MOT)
- Video instance segmentation (VIS)
-
The First Unified Video Perception Platform
We are the first open source toolbox that unifies versatile video perception tasks including video object detection, multiple object tracking, single object tracking and video instance segmentation.
-
Modular Design
We decompose the video perception framework into different components and one can easily construct a customized method by combining different modules.
-
Simple, Fast and Strong
Simple: MMTracking interacts with other OpenMMLab projects. It is built upon MMDetection that we can capitalize any detector only through modifying the configs.
Fast: All operations run on GPUs. The training and inference speeds are faster than or comparable to other implementations.
Strong: We reproduce state-of-the-art models and some of them even outperform the official implementations.
Please refer to get_started.md for the basic usage of MMTracking.
A Colab tutorial is provided. You may preview the notebook here or directly run it on Colab.
There are some basic usage guides, including:
If you want to learn more advanced guides, you can refer to:
- data flow
- structures
- models
- datasets
- transforms
- evaluation
- engine
- convention
- add modules
- add datasets
- add transforms
- add metrics
- customized runtime
Results and models are available in the model zoo.
We appreciate all contributions to improve MMTracking. Please refer to CONTRIBUTING.md for the contributing guideline and this discussion for development roadmap.
If you encounter any problems in the process of using MMTracking, you can firstly refer to FAQ. If not solved, you can post an issue and we will give a response as soon as possible.