📘Documentation | 🛠️Installation | 👀Model Zoo | 🆕Update News | 🤔Reporting Issues
English
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 1.5+.
Please refer to get_started.md for installation and dataset_prepare.md for dataset preparation.
MMSegmentation is based on modular design. Developer can only modify configuration templates that contain the modules of data enhancement strategies, backbone networks, loss functions and other different components for actual application scenarios. There are some tutorials for different modular configurations:
- configuration
- customizing dataset
- designing data pipeline
- customizing modules
- customizing runtime
- training tricks
- useful tools
See train.md and inference.md for the basic usage of MMSegmentation.
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 (ICCV'2021)
- Twins (NeurIPS'2021)
- BEiT (ICLR'2022)
- ConvNeXt (CVPR'2022)
- MAE (CVPR'2022)
Supported methods:
- FCN (CVPR'2015/TPAMI'2017)
- ERFNet (T-ITS'2017)
- UNet (MICCAI'2016/Nat. Methods'2019)
- PSPNet (CVPR'2017)
- DeepLabV3 (ArXiv'2017)
- BiSeNetV1 (ECCV'2018)
- PSANet (ECCV'2018)
- DeepLabV3+ (CVPR'2018)
- UPerNet (ECCV'2018)
- ICNet (ECCV'2018)
- NonLocal Net (CVPR'2018)
- EncNet (CVPR'2018)
- Semantic FPN (CVPR'2019)
- DANet (CVPR'2019)
- APCNet (CVPR'2019)
- EMANet (ICCV'2019)
- CCNet (ICCV'2019)
- DMNet (ICCV'2019)
- ANN (ICCV'2019)
- GCNet (ICCVW'2019/TPAMI'2020)
- FastFCN (ArXiv'2019)
- Fast-SCNN (ArXiv'2019)
- ISANet (ArXiv'2019/IJCV'2021)
- OCRNet (ECCV'2020)
- DNLNet (ECCV'2020)
- PointRend (CVPR'2020)
- CGNet (TIP'2020)
- BiSeNetV2 (IJCV'2021)
- STDC (CVPR'2021)
- SETR (CVPR'2021)
- DPT (ArXiv'2021)
- Segmenter (ICCV'2021)
- SegFormer (NeurIPS'2021)
- K-Net (NeurIPS'2021)
Please refer to FAQ for frequently asked questions.
MMSegmentation is an open source project that welcome any contribution and feedback. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible as well as standardized toolkit to reimplement existing methods and develop their own new semantic segmentation methods.
If you find this project useful in your research, please consider cite:
@misc{mmseg2020,
title={{MMSegmentation}: OpenMMLab Semantic Segmentation Toolbox and Benchmark},
author={MMSegmentation Contributors},
howpublished = {\url{https://github.com/open-mmlab/mmsegmentation}},
year={2020}
}MMSegmentation is released under the Apache 2.0 license, while some specific features in this library are with other licenses. Please refer to LICENSES.md for the careful check, if you are using our code for commercial matters.