-
谢昕辰 authored* rewrite init function * support dark_zurich test * reset image size * add night * add train_pipeline * init function parameters * remove base dataset config * remove fcn config * update doc * add datasets to README * update doc * fix table of PSPNet config * fix table of PSPNet config * change 'model' tp 'evaluation checkpoint' * fix typos in README_zh-CN Co-authored-by:
MengzhangLI <mcmong@pku.edu.cn>谢昕辰 authored* rewrite init function * support dark_zurich test * reset image size * add night * add train_pipeline * init function parameters * remove base dataset config * remove fcn config * update doc * add datasets to README * update doc * fix table of PSPNet config * fix table of PSPNet config * change 'model' tp 'evaluation checkpoint' * fix typos in README_zh-CN Co-authored-by:MengzhangLI <mcmong@pku.edu.cn>
Documentation: https://mmsegmentation.readthedocs.io/
English | 简体中文
Introduction
MMSegmentation is an open source semantic segmentation toolbox based on PyTorch. It is a part of the OpenMMLab project.
The master branch works with PyTorch 1.3+.
Major features
-
Unified Benchmark
We provide a unified benchmark toolbox for various semantic segmentation methods.
-
Modular Design
We decompose the semantic segmentation framework into different components and one can easily construct a customized semantic segmentation framework by combining different modules.
-
Support of multiple methods out of box
The toolbox directly supports popular and contemporary semantic segmentation frameworks, e.g. PSPNet, DeepLabV3, PSANet, DeepLabV3+, etc.
-
High efficiency
The training speed is faster than or comparable to other codebases.
License
This project is released under the Apache 2.0 license.
Changelog
v0.16.0 was released in 08/04/2021. Please refer to changelog.md for details and release history.
Benchmark and model zoo
Results and models are available in the model zoo.
Supported backbones:
- ResNet (CVPR'2016)
- ResNeXt (CVPR'2017)
- HRNet (CVPR'2019)
- ResNeSt (ArXiv'2020)
- MobileNetV2 (CVPR'2018)
- MobileNetV3 (ICCV'2019)
- Vision Transformer (ICLR'2021)
- Swin Transformer (ArXiv'2021)
Supported methods: