<div align="center">
<img width="600" alt="onedl-mmsegmentation" src="https://raw.githubusercontent.com/VBTI-development/onedl-mmsegmentation/main/resources/onedl-mmseg-logo.png"/>
<div> </div>
<div align="center">
<a href="https://vbti.ai">
<b><font size="5">VBTI Website</font></b>
</a>
<a href="https://onedl.ai">
<b><font size="5">OneDL platform</font></b>
</a>
</div>
<div> </div>
[](https://onedl-mmsegmentation.readthedocs.io/en/latest/)
[](https://github.com/VBTI-development/onedl-mmdetmmsegmentationection/blob/main/LICENSE)
[](https://pypi.org/project/onedl-mmsegmentation/)
[](https://pypi.org/project/onedl-mmsegmentation)
[](https://github.com/VBTI-development/onedl-mmsegmentation/actions/workflows/merge_stage_test.yml)
[](https://github.com/VBTI-development/onedl-mmsegmentation/issues)
[](https://github.com/VBTI-development/onedl-mmsegmentation/issues)
[📘 Documentation](https://onedl-mmsegmentation.readthedocs.io/en/latest/) |
[🛠️ Installation](https://onedl-mmsegmentation.readthedocs.io/en/latest/get_started.html) |
[👀 Model Zoo](https://onedl-mmsegmentation.readthedocs.io/en/latest/model_zoo.html) |
[🆕 Update News](https://onedl-mmsegmentation.readthedocs.io/en/latest/notes/changelog.html) |
[🚀Ongoing Projects](https://github.com/open-mmlab/mmsegmentation/projects) |
[🤔 Reporting Issues](https://github.com/VBTI-development/onedl-mmsegmentation/issues/new/choose) |
## Introduction
MMSegmentation is an open source semantic segmentation toolbox based on PyTorch.
It is a part of the OpenMMLab project.
The [main](https://github.com/open-mmlab/mmsegmentation/tree/main) branch works with PyTorch 2.0+.
### 🎉 Introducing MMSegmentation v1.0.0 🎉
We are thrilled to announce the official release of MMSegmentation's latest version! For this new release, the [main](https://github.com/open-mmlab/mmsegmentation/tree/main) branch serves as the primary branch, while the development branch is [dev-1.x](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x). The stable branch for the previous release remains as the [0.x](https://github.com/open-mmlab/mmsegmentation/tree/0.x) branch. Please note that the [master](https://github.com/open-mmlab/mmsegmentation/tree/master) branch will only be maintained for a limited time before being removed. We encourage you to be mindful of branch selection and updates during use. Thank you for your unwavering support and enthusiasm, and let's work together to make MMSegmentation even more robust and powerful! 💪
MMSegmentation v1.x brings remarkable improvements over the 0.x release, offering a more flexible and feature-packed experience. To utilize the new features in v1.x, we kindly invite you to consult our detailed [📚 migration guide](https://mmsegmentation.readthedocs.io/en/latest/migration/interface.html), which will help you seamlessly transition your projects. Your support is invaluable, and we eagerly await your feedback!
### 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.
## What's New
The VBTI development team is reviving MMLabs code, making it work with
newer pytorch versions and fixing bugs. We are only a small team, so your help
is appreciated.
v1.3.0 was released in August 2025, from 1.2.0 to 1.3.0, we have added or updated the following features:
### Highlights
- Disabled tests on RS_inferencer due to difficulties installing gdal
- Disabled tests on VPD Model due to the latent-diffusion needing to be installed in editable mode. This is not playing nice with uv.
## Installation
Please refer to [get_started.md](docs/en/get_started.md#installation) for installation and [dataset_prepare.md](docs/en/user_guides/2_dataset_prepare.md#prepare-datasets) for dataset preparation.
## Get Started
Please see [Overview](docs/en/overview.md) for the general introduction of MMSegmentation.
Please see [user guides](https://mmsegmentation.readthedocs.io/en/latest/user_guides/index.html#) for the basic usage of MMSegmentation.
There are also [advanced tutorials](https://mmsegmentation.readthedocs.io/en/latest/advanced_guides/index.html) for in-depth understanding of mmseg design and implementation .
A Colab tutorial is also provided. You may preview the notebook [here](demo/MMSegmentation_Tutorial.ipynb) or directly [run](https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/main/demo/MMSegmentation_Tutorial.ipynb) on Colab.
To migrate from MMSegmentation 0.x, please refer to [migration](docs/en/migration).
## Tutorial
<div align="center">
<b>MMSegmentation Tutorials</b>
</div>
<table align="center">
<tbody>
<tr align="center" valign="center">
<td>
<b>Get Started</b>
</td>
<td>
<b>MMSeg Basic Tutorial</b>
</td>
<td>
<b>MMSeg Detail Tutorial</b>
</td>
<td>
<b>MMSeg Development Tutorial</b>
</td>
</tr>
<tr valign="top">
<td>
<ul>
<li><a href="docs/en/overview.md">MMSeg overview</a></li>
<li><a href="docs/en/get_started.md">MMSeg Installation</a></li>
<li><a href="docs/en/notes/faq.md">FAQ</a></li>
</ul>
</td>
<td>
<ul>
<li><a href="docs/en/user_guides/1_config.md">Tutorial 1: Learn about Configs</a></li>
<li><a href="docs/en/user_guides/2_dataset_prepare.md">Tutorial 2: Prepare datasets</a></li>
<li><a href="docs/en/user_guides/3_inference.md">Tutorial 3: Inference with existing models</a></li>
<li><a href="docs/en/user_guides/4_train_test.md">Tutorial 4: Train and test with existing models</a></li>
<li><a href="docs/en/user_guides/5_deployment.md">Tutorial 5: Model deployment</a></li>
<li><a href="docs/zh_cn/user_guides/deploy_jetson.md">Deploy mmsegmentation on Jetson platform</a></li>
<li><a href="docs/en/user_guides/useful_tools.md">Useful Tools</a></li>
<li><a href="docs/en/user_guides/visualization_feature_map.md">Feature Map Visualization</a></li>
<li><a href="docs/en/user_guides/visualization.md">Visualization</a></li>
</ul>
</td>
<td>
<ul>
<li><a href="docs/en/advanced_guides/datasets.md">MMSeg Dataset</a></li>
<li><a href="docs/en/advanced_guides/models.md">MMSeg Models</a></li>
<li><a href="docs/en/advanced_guides/structures.md">MMSeg Dataset Structures</a></li>
<li><a href="docs/en/advanced_guides/transforms.md">MMSeg Data Transforms</a></li>
<li><a href="docs/en/advanced_guides/data_flow.md">MMSeg Dataflow</a></li>
<li><a href="docs/en/advanced_guides/engine.md">MMSeg Training Engine</a></li>
<li><a href="docs/en/advanced_guides/evaluation.md">MMSeg Evaluation</a></li>
</ul>
</td>
<td>
<ul>
<li><a href="docs/en/advanced_guides/add_datasets.md">Add New Datasets</a></li>
<li><a href="docs/en/advanced_guides/add_metrics.md">Add New Metrics</a></li>
<li><a href="docs/en/advanced_guides/add_models.md">Add New Modules</a></li>
<li><a href="docs/en/advanced_guides/add_transforms.md">Add New Data Transforms</a></li>
<li><a href="docs/en/advanced_guides/customize_runtime.md">Customize Runtime Settings</a></li>
<li><a href="docs/en/advanced_guides/training_tricks.md">Training Tricks</a></li>
<li><a href=".github/CONTRIBUTING.md">Contribute code to MMSeg</a></li>
<li><a href="docs/zh_cn/advanced_guides/contribute_dataset.md">Contribute a standard dataset in projects</a></li>
<li><a href="docs/en/device/npu.md">NPU (HUAWEI Ascend)</a></li>
<li><a href="docs/en/migration/interface.md">0.x → 1.x migration</a></li>
<li><a href="docs/en/migration/package.md">0.x → 1.x package</a></li>
</ul>
</td>
</tr>
</tbody>
</table>
## Benchmark and model zoo
Results and models are available in the [model zoo](docs/en/model_zoo.md).
<div align="center">
<b>Overview</b>
</div>
<table align="center">
<tbody>
<tr align="center" valign="center">
<td>
<b>Supported backbones</b>
</td>
<td>
<b>Supported methods</b>
</td>
<td>
<b>Supported Head</b>
</td>
<td>
<b>Supported datasets</b>
</td>
<td>
<b>Other</b>
</td>
</tr>
<tr valign="top">
<td>
<ul>
<li><a href="mmseg/models/backbones/resnet.py">ResNet(CVPR'2016)</a></li>
<li><a href="mmseg/models/backbones/resnext.py">ResNeXt (CVPR'2017)</a></li>
<li><a href="configs/hrnet">HRNet (CVPR'2019)</a></li>
<li><a href="configs/resnest">ResNeSt (ArXiv'2020)</a></li>
<li><a href="configs/mobilenet_v2">MobileNetV2 (CVPR'2018)</a></li>
<li><a href="configs/mobilenet_v3">MobileNetV3 (ICCV'2019)</a></li>
<li><a href="configs/vit">Vision Transformer (ICLR'2021)</a></li>
<li><a href="configs/swin">Swin Transformer (ICCV'2021)</a></li>
<li><a href="configs/twins">Twins (NeurIPS'2021)</a></li>
<li><a href="configs/beit">BEiT (ICLR'2022)</a></li>
<li><a href="configs/convnext">ConvNeXt (CVPR'2022)</a></li>
<li><a href="configs/mae">MAE (CVPR'2022)</a></li>
<li><a href="configs/poolformer">PoolFormer (CVPR'2022)</a></li>
<li><a href="configs/segnext">SegNeXt (NeurIPS'2022)</a></li>
</ul>
</td>
<td>
<ul>
<li><a href="configs/san/">SAN (CVPR'2023)</a></li>
<li><a href="configs/vpd">VPD (ICCV'2023)</a></li>
<li><a href="configs/ddrnet">DDRNet (T-ITS'2022)</a></li>
<li><a href="configs/pidnet">PIDNet (ArXiv'2022)</a></li>
<li><a href="configs/mask2former">Mask2Former (CVPR'2022)</a></li>
<li><a href="configs/maskformer">MaskFormer (NeurIPS'2021)</a></li>
<li><a href="configs/knet">K-Net (NeurIPS'2021)</a></li>
<li><a href="configs/segformer">SegFormer (NeurIPS'2021)</a></li>
<li><a href="configs/segmenter">Segmenter (ICCV'2021)</a></li>
<li><a href="configs/dpt">DPT (ArXiv'2021)</a></li>
<li><a href="configs/setr">SETR (CVPR'2021)</a></li>
<li><a href="configs/stdc">STDC (CVPR'2021)</a></li>
<li><a href="configs/bisenetv2">BiSeNetV2 (IJCV'2021)</a></li>
<li><a href="configs/cgnet">CGNet (TIP'2020)</a></li>
<li><a href="configs/point_rend">PointRend (CVPR'2020)</a></li>
<li><a href="configs/dnlnet">DNLNet (ECCV'2020)</a></li>
<li><a href="configs/ocrnet">OCRNet (ECCV'2020)</a></li>
<li><a href="configs/isanet">ISANet (ArXiv'2019/IJCV'2021)</a></li>
<li><a href="configs/fastscnn">Fast-SCNN (ArXiv'2019)</a></li>
<li><a href="configs/fastfcn">FastFCN (ArXiv'2019)</a></li>
<li><a href="configs/gcnet">GCNet (ICCVW'2019/TPAMI'2020)</a></li>
<li><a href="configs/ann">ANN (ICCV'2019)</a></li>
<li><a href="configs/emanet">EMANet (ICCV'2019)</a></li>
<li><a href="configs/ccnet">CCNet (ICCV'2019)</a></li>
<li><a href="configs/dmnet">DMNet (ICCV'2019)</a></li>
<li><a href="configs/sem_fpn">Semantic FPN (CVPR'2019)</a></li>
<li><a href="configs/danet">DANet (CVPR'2019)</a></li>
<li><a href="configs/apcnet">APCNet (CVPR'2019)</a></li>
<li><a href="configs/nonlocal_net">NonLocal Net (CVPR'2018)</a></li>
<li><a href="configs/encnet">EncNet (CVPR'2018)</a></li>
<li><a href="configs/deeplabv3plus">DeepLabV3+ (CVPR'2018)</a></li>
<li><a href="configs/upernet">UPerNet (ECCV'2018)</a></li>
<li><a href="configs/icnet">ICNet (ECCV'2018)</a></li>
<li><a href="configs/psanet">PSANet (ECCV'2018)</a></li>
<li><a href="configs/bisenetv1">BiSeNetV1 (ECCV'2018)</a></li>
<li><a href="configs/deeplabv3">DeepLabV3 (ArXiv'2017)</a></li>
<li><a href="configs/pspnet">PSPNet (CVPR'2017)</a></li>
<li><a href="configs/erfnet">ERFNet (T-ITS'2017)</a></li>
<li><a href="configs/unet">UNet (MICCAI'2016/Nat. Methods'2019)</a></li>
<li><a href="configs/fcn">FCN (CVPR'2015/TPAMI'2017)</a></li>
</ul>
</td>
<td>
<ul>
<li><a href="mmseg/models/decode_heads/ann_head.py">ANN_Head</li>
<li><a href="mmseg/models/decode_heads/apc_head.py">APC_Head</li>
<li><a href="mmseg/models/decode_heads/aspp_head.py">ASPP_Head</li>
<li><a href="mmseg/models/decode_heads/cc_head.py">CC_Head</li>
<li><a href="mmseg/models/decode_heads/da_head.py">DA_Head</li>
<li><a href="mmseg/models/decode_heads/ddr_head.py">DDR_Head</li>
<li><a href="mmseg/models/decode_heads/dm_head.py">DM_Head</li>
<li><a href="mmseg/models/decode_heads/dnl_head.py">DNL_Head</li>
<li><a href="mmseg/models/decode_heads/dpt_head.py">DPT_HEAD</li>
<li><a href="mmseg/models/decode_heads/ema_head.py">EMA_Head</li>
<li><a href="mmseg/models/decode_heads/enc_head.py">ENC_Head</li>
<li><a href="mmseg/models/decode_heads/fcn_head.py">FCN_Head</li>
<li><a href="mmseg/models/decode_heads/fpn_head.py">FPN_Head</li>
<li><a href="mmseg/models/decode_heads/gc_head.py">GC_Head</li>
<li><a href="mmseg/models/decode_heads/ham_head.py">LightHam_Head</li>
<li><a href="mmseg/models/decode_heads/isa_head.py">ISA_Head</li>
<li><a href="mmseg/models/decode_heads/knet_head.py">Knet_Head</li>
<li><a href="mmseg/models/decode_heads/lraspp_head.py">LRASPP_Head</li>
<li><a href="mmseg/models/decode_heads/mask2former_head.py">mask2former_Head</li>
<li><a href="mmseg/models/decode_heads/maskformer_head.py">maskformer_Head</li>
<li><a href="mmseg/models/decode_heads/nl_head.py">NL_Head</li>
<li><a href="mmseg/models/decode_heads/ocr_head.py">OCR_Head</li>
<li><a href="mmseg/models/decode_heads/pid_head.py">PID_Head</li>
<li><a href="mmseg/models/decode_heads/point_head.py">point_Head</li>
<li><a href="mmseg/models/decode_heads/psa_head.py">PSA_Head</li>
<li><a href="mmseg/models/decode_heads/psp_head.py">PSP_Head</li>
<li><a href="mmseg/models/decode_heads/san_head.py">SAN_Head</li>
<li><a href="mmseg/models/decode_heads/segformer_head.py">segformer_Head</li>
<li><a href="mmseg/models/decode_heads/segmenter_mask_head.py">segmenter_mask_Head</li>
<li><a href="mmseg/models/decode_heads/sep_aspp_head.py">SepASPP_Head</li>
<li><a href="mmseg/models/decode_heads/sep_fcn_head.py">SepFCN_Head</li>
<li><a href="mmseg/models/decode_heads/setr_mla_head.py">SETRMLAHead_Head</li>
<li><a href="mmseg/models/decode_heads/setr_up_head.py">SETRUP_Head</li>
<li><a href="mmseg/models/decode_heads/stdc_head.py">STDC_Head</li>
<li><a href="mmseg/models/decode_heads/uper_head.py">Uper_Head</li>
<li><a href="mmseg/models/decode_heads/vpd_depth_head.py">VPDDepth_Head</li>
</ul>
</td>
<td>
<ul>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#cityscapes">Cityscapes</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#pascal-voc">PASCAL VOC</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#ade20k">ADE20K</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#pascal-context">Pascal Context</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#coco-stuff-10k">COCO-Stuff 10k</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#coco-stuff-164k">COCO-Stuff 164k</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#chase-db1">CHASE_DB1</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#drive">DRIVE</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#hrf">HRF</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#stare">STARE</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#dark-zurich">Dark Zurich</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#nighttime-driving">Nighttime Driving</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#loveda">LoveDA</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#isprs-potsdam">Potsdam</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#isprs-vaihingen">Vaihingen</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#isaid">iSAID</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#mapillary-vistas-datasets">Mapillary Vistas</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#levir-cd">LEVIR-CD</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#bdd100K">BDD100K</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#nyu">NYU</a></li>
<li><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#hsi-drive-2.0">HSIDrive20</a></li>
</ul>
</td>
<td>
<ul>
<li><b>Supported loss</b></li>
<ul>
<li><a href="mmseg/models/losses/boundary_loss.py">boundary_loss</a></li>
<li><a href="mmseg/models/losses/cross_entropy_loss.py">cross_entropy_loss</a></li>
<li><a href="mmseg/models/losses/dice_loss.py">dice_loss</a></li>
<li><a href="mmseg/models/losses/focal_loss.py">focal_loss</a></li>
<li><a href="mmseg/models/losses/huasdorff_distance_loss.py">huasdorff_distance_loss</a></li>
<li><a href="mmseg/models/losses/kldiv_loss.py">kldiv_loss</a></li>
<li><a href="mmseg/models/losses/lovasz_loss.py">lovasz_loss</a></li>
<li><a href="mmseg/models/losses/ohem_cross_entropy_loss.py">ohem_cross_entropy_loss</a></li>
<li><a href="mmseg/models/losses/silog_loss.py">silog_loss</a></li>
<li><a href="mmseg/models/losses/tversky_loss.py">tversky_loss</a></li>
</ul>
</ul>
</td>
</tbody>
</table>
Please refer to [FAQ](docs/en/notes/faq.md) for frequently asked questions.
## Projects
[Here](projects/README.md) are some implementations of SOTA models and solutions built on MMSegmentation, which are supported and maintained by community users. These projects demonstrate the best practices based on MMSegmentation for research and product development. We welcome and appreciate all the contributions to OpenMMLab ecosystem.
## Contributing
We appreciate all contributions to improve MMSegmentation. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
## Acknowledgement
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.
## Citation
If you find this project useful in your research, please consider cite:
```bibtex
@misc{mmseg2020,
title={{MMSegmentation}: OpenMMLab Semantic Segmentation Toolbox and Benchmark},
author={MMSegmentation Contributors},
howpublished = {\url{https://github.com/open-mmlab/mmsegmentation}},
year={2020}
}
```
## License
This project is released under the [Apache 2.0 license](LICENSE).
## Projects in VBTI-development
- [MMEngine](https://github.com/vbti-development/onedl-mmengine): OpenMMLab foundational library for training deep learning models.
- [MMCV](https://github.com/vbti-development/onedl-mmcv): OpenMMLab foundational library for computer vision.
- [MMPreTrain](https://github.com/vbti-development/onedl-mmpretrain): OpenMMLab pre-training toolbox and benchmark.
- [MMDetection](https://github.com/vbti-development/onedl-mmdetection): OpenMMLab detection toolbox and benchmark.
- [MMRotate](https://github.com/vbti-development/onedl-mmrotate): OpenMMLab rotated object detection toolbox and benchmark.
- [MMSegmentation](https://github.com/vbti-development/onedl-mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.
- [MMDeploy](https://github.com/vbti-development/onedl-mmdeploy): OpenMMLab model deployment framework.
- [MIM](https://github.com/vbti-development/onedl-mim): MIM installs OpenMMLab packages.
## Projects in OpenMMLab
- [MMagic](https://github.com/open-mmlab/mmagic): Open**MM**Lab **A**dvanced, **G**enerative and **I**ntelligent **C**reation toolbox.
- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.
- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO series toolbox and benchmark.
- [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox.
- [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.
- [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 3D human parametric model toolbox and benchmark.
- [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab self-supervised learning toolbox and benchmark.
- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab model compression toolbox and benchmark.
- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab fewshot learning toolbox and benchmark.
- [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark.
- [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.
- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark.
- [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.
- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox.
- [MMEval](https://github.com/open-mmlab/mmeval): A unified evaluation library for multiple machine learning libraries.
- [Playground](https://github.com/open-mmlab/playground): A central hub for gathering and showcasing amazing projects built upon OpenMMLab.
Raw data
{
"_id": null,
"home_page": null,
"name": "onedl-mmsegmentation",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "computer vision, semantic segmentation",
"author": "MMSegmentation Contributors",
"author_email": "VBTI Software Team <oss@vbti.nl>",
"download_url": "https://files.pythonhosted.org/packages/74/ca/93a94e0ff32354a33cc9583c476036824577dcbbe8cb4874d17246f07137/onedl_mmsegmentation-1.3.0rc0.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <img width=\"600\" alt=\"onedl-mmsegmentation\" src=\"https://raw.githubusercontent.com/VBTI-development/onedl-mmsegmentation/main/resources/onedl-mmseg-logo.png\"/>\n <div> </div>\n <div align=\"center\">\n <a href=\"https://vbti.ai\">\n <b><font size=\"5\">VBTI Website</font></b>\n </a>\n \n <a href=\"https://onedl.ai\">\n <b><font size=\"5\">OneDL platform</font></b>\n </a>\n </div>\n<div> </div>\n\n[](https://onedl-mmsegmentation.readthedocs.io/en/latest/)\n[](https://github.com/VBTI-development/onedl-mmdetmmsegmentationection/blob/main/LICENSE)\n\n[](https://pypi.org/project/onedl-mmsegmentation/)\n[](https://pypi.org/project/onedl-mmsegmentation)\n\n[](https://github.com/VBTI-development/onedl-mmsegmentation/actions/workflows/merge_stage_test.yml)\n[](https://github.com/VBTI-development/onedl-mmsegmentation/issues)\n[](https://github.com/VBTI-development/onedl-mmsegmentation/issues)\n\n[\ud83d\udcd8 Documentation](https://onedl-mmsegmentation.readthedocs.io/en/latest/) |\n[\ud83d\udee0\ufe0f Installation](https://onedl-mmsegmentation.readthedocs.io/en/latest/get_started.html) |\n[\ud83d\udc40 Model Zoo](https://onedl-mmsegmentation.readthedocs.io/en/latest/model_zoo.html) |\n[\ud83c\udd95 Update News](https://onedl-mmsegmentation.readthedocs.io/en/latest/notes/changelog.html) |\n[\ud83d\ude80Ongoing Projects](https://github.com/open-mmlab/mmsegmentation/projects) |\n[\ud83e\udd14 Reporting Issues](https://github.com/VBTI-development/onedl-mmsegmentation/issues/new/choose) |\n\n## Introduction\n\nMMSegmentation is an open source semantic segmentation toolbox based on PyTorch.\nIt is a part of the OpenMMLab project.\n\nThe [main](https://github.com/open-mmlab/mmsegmentation/tree/main) branch works with PyTorch 2.0+.\n\n### \ud83c\udf89 Introducing MMSegmentation v1.0.0 \ud83c\udf89\n\nWe are thrilled to announce the official release of MMSegmentation's latest version! For this new release, the [main](https://github.com/open-mmlab/mmsegmentation/tree/main) branch serves as the primary branch, while the development branch is [dev-1.x](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x). The stable branch for the previous release remains as the [0.x](https://github.com/open-mmlab/mmsegmentation/tree/0.x) branch. Please note that the [master](https://github.com/open-mmlab/mmsegmentation/tree/master) branch will only be maintained for a limited time before being removed. We encourage you to be mindful of branch selection and updates during use. Thank you for your unwavering support and enthusiasm, and let's work together to make MMSegmentation even more robust and powerful! \ud83d\udcaa\n\nMMSegmentation v1.x brings remarkable improvements over the 0.x release, offering a more flexible and feature-packed experience. To utilize the new features in v1.x, we kindly invite you to consult our detailed [\ud83d\udcda migration guide](https://mmsegmentation.readthedocs.io/en/latest/migration/interface.html), which will help you seamlessly transition your projects. Your support is invaluable, and we eagerly await your feedback!\n\n\n\n### Major features\n\n- **Unified Benchmark**\n\n We provide a unified benchmark toolbox for various semantic segmentation methods.\n\n- **Modular Design**\n\n We decompose the semantic segmentation framework into different components and one can easily construct a customized semantic segmentation framework by combining different modules.\n\n- **Support of multiple methods out of box**\n\n The toolbox directly supports popular and contemporary semantic segmentation frameworks, *e.g.* PSPNet, DeepLabV3, PSANet, DeepLabV3+, etc.\n\n- **High efficiency**\n\n The training speed is faster than or comparable to other codebases.\n\n## What's New\n\nThe VBTI development team is reviving MMLabs code, making it work with\nnewer pytorch versions and fixing bugs. We are only a small team, so your help\nis appreciated.\n\nv1.3.0 was released in August 2025, from 1.2.0 to 1.3.0, we have added or updated the following features:\n\n### Highlights\n\n- Disabled tests on RS_inferencer due to difficulties installing gdal\n- Disabled tests on VPD Model due to the latent-diffusion needing to be installed in editable mode. This is not playing nice with uv.\n\n## Installation\n\nPlease refer to [get_started.md](docs/en/get_started.md#installation) for installation and [dataset_prepare.md](docs/en/user_guides/2_dataset_prepare.md#prepare-datasets) for dataset preparation.\n\n## Get Started\n\nPlease see [Overview](docs/en/overview.md) for the general introduction of MMSegmentation.\n\nPlease see [user guides](https://mmsegmentation.readthedocs.io/en/latest/user_guides/index.html#) for the basic usage of MMSegmentation.\nThere are also [advanced tutorials](https://mmsegmentation.readthedocs.io/en/latest/advanced_guides/index.html) for in-depth understanding of mmseg design and implementation .\n\nA Colab tutorial is also provided. You may preview the notebook [here](demo/MMSegmentation_Tutorial.ipynb) or directly [run](https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/main/demo/MMSegmentation_Tutorial.ipynb) on Colab.\n\nTo migrate from MMSegmentation 0.x, please refer to [migration](docs/en/migration).\n\n## Tutorial\n\n<div align=\"center\">\n <b>MMSegmentation Tutorials</b>\n</div>\n<table align=\"center\">\n <tbody>\n <tr align=\"center\" valign=\"center\">\n <td>\n <b>Get Started</b>\n </td>\n <td>\n <b>MMSeg Basic Tutorial</b>\n </td>\n <td>\n <b>MMSeg Detail Tutorial</b>\n </td>\n <td>\n <b>MMSeg Development Tutorial</b>\n </td>\n </tr>\n <tr valign=\"top\">\n <td>\n <ul>\n <li><a href=\"docs/en/overview.md\">MMSeg overview</a></li>\n <li><a href=\"docs/en/get_started.md\">MMSeg Installation</a></li>\n <li><a href=\"docs/en/notes/faq.md\">FAQ</a></li>\n </ul>\n </td>\n <td>\n <ul>\n <li><a href=\"docs/en/user_guides/1_config.md\">Tutorial 1: Learn about Configs</a></li>\n <li><a href=\"docs/en/user_guides/2_dataset_prepare.md\">Tutorial 2: Prepare datasets</a></li>\n <li><a href=\"docs/en/user_guides/3_inference.md\">Tutorial 3: Inference with existing models</a></li>\n <li><a href=\"docs/en/user_guides/4_train_test.md\">Tutorial 4: Train and test with existing models</a></li>\n <li><a href=\"docs/en/user_guides/5_deployment.md\">Tutorial 5: Model deployment</a></li>\n <li><a href=\"docs/zh_cn/user_guides/deploy_jetson.md\">Deploy mmsegmentation on Jetson platform</a></li>\n <li><a href=\"docs/en/user_guides/useful_tools.md\">Useful Tools</a></li>\n <li><a href=\"docs/en/user_guides/visualization_feature_map.md\">Feature Map Visualization</a></li>\n <li><a href=\"docs/en/user_guides/visualization.md\">Visualization</a></li>\n </ul>\n </td>\n <td>\n <ul>\n <li><a href=\"docs/en/advanced_guides/datasets.md\">MMSeg Dataset</a></li>\n <li><a href=\"docs/en/advanced_guides/models.md\">MMSeg Models</a></li>\n <li><a href=\"docs/en/advanced_guides/structures.md\">MMSeg Dataset Structures</a></li>\n <li><a href=\"docs/en/advanced_guides/transforms.md\">MMSeg Data Transforms</a></li>\n <li><a href=\"docs/en/advanced_guides/data_flow.md\">MMSeg Dataflow</a></li>\n <li><a href=\"docs/en/advanced_guides/engine.md\">MMSeg Training Engine</a></li>\n <li><a href=\"docs/en/advanced_guides/evaluation.md\">MMSeg Evaluation</a></li>\n </ul>\n </td>\n <td>\n <ul>\n <li><a href=\"docs/en/advanced_guides/add_datasets.md\">Add New Datasets</a></li>\n <li><a href=\"docs/en/advanced_guides/add_metrics.md\">Add New Metrics</a></li>\n <li><a href=\"docs/en/advanced_guides/add_models.md\">Add New Modules</a></li>\n <li><a href=\"docs/en/advanced_guides/add_transforms.md\">Add New Data Transforms</a></li>\n <li><a href=\"docs/en/advanced_guides/customize_runtime.md\">Customize Runtime Settings</a></li>\n <li><a href=\"docs/en/advanced_guides/training_tricks.md\">Training Tricks</a></li>\n <li><a href=\".github/CONTRIBUTING.md\">Contribute code to MMSeg</a></li>\n <li><a href=\"docs/zh_cn/advanced_guides/contribute_dataset.md\">Contribute a standard dataset in projects</a></li>\n <li><a href=\"docs/en/device/npu.md\">NPU (HUAWEI Ascend)</a></li>\n <li><a href=\"docs/en/migration/interface.md\">0.x \u2192 1.x migration</a></li>\n <li><a href=\"docs/en/migration/package.md\">0.x \u2192 1.x package</a></li>\n </ul>\n </td>\n </tr>\n </tbody>\n</table>\n\n## Benchmark and model zoo\n\nResults and models are available in the [model zoo](docs/en/model_zoo.md).\n\n<div align=\"center\">\n <b>Overview</b>\n</div>\n<table align=\"center\">\n <tbody>\n <tr align=\"center\" valign=\"center\">\n <td>\n <b>Supported backbones</b>\n </td>\n <td>\n <b>Supported methods</b>\n </td>\n <td>\n <b>Supported Head</b>\n </td>\n <td>\n <b>Supported datasets</b>\n </td>\n <td>\n <b>Other</b>\n </td>\n </tr>\n <tr valign=\"top\">\n <td>\n <ul>\n <li><a href=\"mmseg/models/backbones/resnet.py\">ResNet(CVPR'2016)</a></li>\n <li><a href=\"mmseg/models/backbones/resnext.py\">ResNeXt (CVPR'2017)</a></li>\n <li><a href=\"configs/hrnet\">HRNet (CVPR'2019)</a></li>\n <li><a href=\"configs/resnest\">ResNeSt (ArXiv'2020)</a></li>\n <li><a href=\"configs/mobilenet_v2\">MobileNetV2 (CVPR'2018)</a></li>\n <li><a href=\"configs/mobilenet_v3\">MobileNetV3 (ICCV'2019)</a></li>\n <li><a href=\"configs/vit\">Vision Transformer (ICLR'2021)</a></li>\n <li><a href=\"configs/swin\">Swin Transformer (ICCV'2021)</a></li>\n <li><a href=\"configs/twins\">Twins (NeurIPS'2021)</a></li>\n <li><a href=\"configs/beit\">BEiT (ICLR'2022)</a></li>\n <li><a href=\"configs/convnext\">ConvNeXt (CVPR'2022)</a></li>\n <li><a href=\"configs/mae\">MAE (CVPR'2022)</a></li>\n <li><a href=\"configs/poolformer\">PoolFormer (CVPR'2022)</a></li>\n <li><a href=\"configs/segnext\">SegNeXt (NeurIPS'2022)</a></li>\n </ul>\n </td>\n <td>\n <ul>\n <li><a href=\"configs/san/\">SAN (CVPR'2023)</a></li>\n <li><a href=\"configs/vpd\">VPD (ICCV'2023)</a></li>\n <li><a href=\"configs/ddrnet\">DDRNet (T-ITS'2022)</a></li>\n <li><a href=\"configs/pidnet\">PIDNet (ArXiv'2022)</a></li>\n <li><a href=\"configs/mask2former\">Mask2Former (CVPR'2022)</a></li>\n <li><a href=\"configs/maskformer\">MaskFormer (NeurIPS'2021)</a></li>\n <li><a href=\"configs/knet\">K-Net (NeurIPS'2021)</a></li>\n <li><a href=\"configs/segformer\">SegFormer (NeurIPS'2021)</a></li>\n <li><a href=\"configs/segmenter\">Segmenter (ICCV'2021)</a></li>\n <li><a href=\"configs/dpt\">DPT (ArXiv'2021)</a></li>\n <li><a href=\"configs/setr\">SETR (CVPR'2021)</a></li>\n <li><a href=\"configs/stdc\">STDC (CVPR'2021)</a></li>\n <li><a href=\"configs/bisenetv2\">BiSeNetV2 (IJCV'2021)</a></li>\n <li><a href=\"configs/cgnet\">CGNet (TIP'2020)</a></li>\n <li><a href=\"configs/point_rend\">PointRend (CVPR'2020)</a></li>\n <li><a href=\"configs/dnlnet\">DNLNet (ECCV'2020)</a></li>\n <li><a href=\"configs/ocrnet\">OCRNet (ECCV'2020)</a></li>\n <li><a href=\"configs/isanet\">ISANet (ArXiv'2019/IJCV'2021)</a></li>\n <li><a href=\"configs/fastscnn\">Fast-SCNN (ArXiv'2019)</a></li>\n <li><a href=\"configs/fastfcn\">FastFCN (ArXiv'2019)</a></li>\n <li><a href=\"configs/gcnet\">GCNet (ICCVW'2019/TPAMI'2020)</a></li>\n <li><a href=\"configs/ann\">ANN (ICCV'2019)</a></li>\n <li><a href=\"configs/emanet\">EMANet (ICCV'2019)</a></li>\n <li><a href=\"configs/ccnet\">CCNet (ICCV'2019)</a></li>\n <li><a href=\"configs/dmnet\">DMNet (ICCV'2019)</a></li>\n <li><a href=\"configs/sem_fpn\">Semantic FPN (CVPR'2019)</a></li>\n <li><a href=\"configs/danet\">DANet (CVPR'2019)</a></li>\n <li><a href=\"configs/apcnet\">APCNet (CVPR'2019)</a></li>\n <li><a href=\"configs/nonlocal_net\">NonLocal Net (CVPR'2018)</a></li>\n <li><a href=\"configs/encnet\">EncNet (CVPR'2018)</a></li>\n <li><a href=\"configs/deeplabv3plus\">DeepLabV3+ (CVPR'2018)</a></li>\n <li><a href=\"configs/upernet\">UPerNet (ECCV'2018)</a></li>\n <li><a href=\"configs/icnet\">ICNet (ECCV'2018)</a></li>\n <li><a href=\"configs/psanet\">PSANet (ECCV'2018)</a></li>\n <li><a href=\"configs/bisenetv1\">BiSeNetV1 (ECCV'2018)</a></li>\n <li><a href=\"configs/deeplabv3\">DeepLabV3 (ArXiv'2017)</a></li>\n <li><a href=\"configs/pspnet\">PSPNet (CVPR'2017)</a></li>\n <li><a href=\"configs/erfnet\">ERFNet (T-ITS'2017)</a></li>\n <li><a href=\"configs/unet\">UNet (MICCAI'2016/Nat. Methods'2019)</a></li>\n <li><a href=\"configs/fcn\">FCN (CVPR'2015/TPAMI'2017)</a></li>\n </ul>\n </td>\n <td>\n <ul>\n <li><a href=\"mmseg/models/decode_heads/ann_head.py\">ANN_Head</li>\n <li><a href=\"mmseg/models/decode_heads/apc_head.py\">APC_Head</li>\n <li><a href=\"mmseg/models/decode_heads/aspp_head.py\">ASPP_Head</li>\n <li><a href=\"mmseg/models/decode_heads/cc_head.py\">CC_Head</li>\n <li><a href=\"mmseg/models/decode_heads/da_head.py\">DA_Head</li>\n <li><a href=\"mmseg/models/decode_heads/ddr_head.py\">DDR_Head</li>\n <li><a href=\"mmseg/models/decode_heads/dm_head.py\">DM_Head</li>\n <li><a href=\"mmseg/models/decode_heads/dnl_head.py\">DNL_Head</li>\n <li><a href=\"mmseg/models/decode_heads/dpt_head.py\">DPT_HEAD</li>\n <li><a href=\"mmseg/models/decode_heads/ema_head.py\">EMA_Head</li>\n <li><a href=\"mmseg/models/decode_heads/enc_head.py\">ENC_Head</li>\n <li><a href=\"mmseg/models/decode_heads/fcn_head.py\">FCN_Head</li>\n <li><a href=\"mmseg/models/decode_heads/fpn_head.py\">FPN_Head</li>\n <li><a href=\"mmseg/models/decode_heads/gc_head.py\">GC_Head</li>\n <li><a href=\"mmseg/models/decode_heads/ham_head.py\">LightHam_Head</li>\n <li><a href=\"mmseg/models/decode_heads/isa_head.py\">ISA_Head</li>\n <li><a href=\"mmseg/models/decode_heads/knet_head.py\">Knet_Head</li>\n <li><a href=\"mmseg/models/decode_heads/lraspp_head.py\">LRASPP_Head</li>\n <li><a href=\"mmseg/models/decode_heads/mask2former_head.py\">mask2former_Head</li>\n <li><a href=\"mmseg/models/decode_heads/maskformer_head.py\">maskformer_Head</li>\n <li><a href=\"mmseg/models/decode_heads/nl_head.py\">NL_Head</li>\n <li><a href=\"mmseg/models/decode_heads/ocr_head.py\">OCR_Head</li>\n <li><a href=\"mmseg/models/decode_heads/pid_head.py\">PID_Head</li>\n <li><a href=\"mmseg/models/decode_heads/point_head.py\">point_Head</li>\n <li><a href=\"mmseg/models/decode_heads/psa_head.py\">PSA_Head</li>\n <li><a href=\"mmseg/models/decode_heads/psp_head.py\">PSP_Head</li>\n <li><a href=\"mmseg/models/decode_heads/san_head.py\">SAN_Head</li>\n <li><a href=\"mmseg/models/decode_heads/segformer_head.py\">segformer_Head</li>\n <li><a href=\"mmseg/models/decode_heads/segmenter_mask_head.py\">segmenter_mask_Head</li>\n <li><a href=\"mmseg/models/decode_heads/sep_aspp_head.py\">SepASPP_Head</li>\n <li><a href=\"mmseg/models/decode_heads/sep_fcn_head.py\">SepFCN_Head</li>\n <li><a href=\"mmseg/models/decode_heads/setr_mla_head.py\">SETRMLAHead_Head</li>\n <li><a href=\"mmseg/models/decode_heads/setr_up_head.py\">SETRUP_Head</li>\n <li><a href=\"mmseg/models/decode_heads/stdc_head.py\">STDC_Head</li>\n <li><a href=\"mmseg/models/decode_heads/uper_head.py\">Uper_Head</li>\n <li><a href=\"mmseg/models/decode_heads/vpd_depth_head.py\">VPDDepth_Head</li>\n </ul>\n </td>\n <td>\n <ul>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#cityscapes\">Cityscapes</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#pascal-voc\">PASCAL VOC</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#ade20k\">ADE20K</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#pascal-context\">Pascal Context</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#coco-stuff-10k\">COCO-Stuff 10k</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#coco-stuff-164k\">COCO-Stuff 164k</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#chase-db1\">CHASE_DB1</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#drive\">DRIVE</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#hrf\">HRF</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#stare\">STARE</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#dark-zurich\">Dark Zurich</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#nighttime-driving\">Nighttime Driving</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#loveda\">LoveDA</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#isprs-potsdam\">Potsdam</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#isprs-vaihingen\">Vaihingen</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#isaid\">iSAID</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#mapillary-vistas-datasets\">Mapillary Vistas</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#levir-cd\">LEVIR-CD</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#bdd100K\">BDD100K</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#nyu\">NYU</a></li>\n <li><a href=\"https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#hsi-drive-2.0\">HSIDrive20</a></li>\n </ul>\n </td>\n <td>\n <ul>\n <li><b>Supported loss</b></li>\n <ul>\n <li><a href=\"mmseg/models/losses/boundary_loss.py\">boundary_loss</a></li>\n <li><a href=\"mmseg/models/losses/cross_entropy_loss.py\">cross_entropy_loss</a></li>\n <li><a href=\"mmseg/models/losses/dice_loss.py\">dice_loss</a></li>\n <li><a href=\"mmseg/models/losses/focal_loss.py\">focal_loss</a></li>\n <li><a href=\"mmseg/models/losses/huasdorff_distance_loss.py\">huasdorff_distance_loss</a></li>\n <li><a href=\"mmseg/models/losses/kldiv_loss.py\">kldiv_loss</a></li>\n <li><a href=\"mmseg/models/losses/lovasz_loss.py\">lovasz_loss</a></li>\n <li><a href=\"mmseg/models/losses/ohem_cross_entropy_loss.py\">ohem_cross_entropy_loss</a></li>\n <li><a href=\"mmseg/models/losses/silog_loss.py\">silog_loss</a></li>\n <li><a href=\"mmseg/models/losses/tversky_loss.py\">tversky_loss</a></li>\n </ul>\n </ul>\n </td>\n </tbody>\n</table>\n\nPlease refer to [FAQ](docs/en/notes/faq.md) for frequently asked questions.\n\n## Projects\n\n[Here](projects/README.md) are some implementations of SOTA models and solutions built on MMSegmentation, which are supported and maintained by community users. These projects demonstrate the best practices based on MMSegmentation for research and product development. We welcome and appreciate all the contributions to OpenMMLab ecosystem.\n\n## Contributing\n\nWe appreciate all contributions to improve MMSegmentation. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.\n\n## Acknowledgement\n\nMMSegmentation is an open source project that welcome any contribution and feedback.\nWe wish that the toolbox and benchmark could serve the growing research\ncommunity by providing a flexible as well as standardized toolkit to reimplement existing methods\nand develop their own new semantic segmentation methods.\n\n## Citation\n\nIf you find this project useful in your research, please consider cite:\n\n```bibtex\n@misc{mmseg2020,\n title={{MMSegmentation}: OpenMMLab Semantic Segmentation Toolbox and Benchmark},\n author={MMSegmentation Contributors},\n howpublished = {\\url{https://github.com/open-mmlab/mmsegmentation}},\n year={2020}\n}\n```\n\n## License\n\nThis project is released under the [Apache 2.0 license](LICENSE).\n\n## Projects in VBTI-development\n\n- [MMEngine](https://github.com/vbti-development/onedl-mmengine): OpenMMLab foundational library for training deep learning models.\n- [MMCV](https://github.com/vbti-development/onedl-mmcv): OpenMMLab foundational library for computer vision.\n- [MMPreTrain](https://github.com/vbti-development/onedl-mmpretrain): OpenMMLab pre-training toolbox and benchmark.\n- [MMDetection](https://github.com/vbti-development/onedl-mmdetection): OpenMMLab detection toolbox and benchmark.\n- [MMRotate](https://github.com/vbti-development/onedl-mmrotate): OpenMMLab rotated object detection toolbox and benchmark.\n- [MMSegmentation](https://github.com/vbti-development/onedl-mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.\n- [MMDeploy](https://github.com/vbti-development/onedl-mmdeploy): OpenMMLab model deployment framework.\n- [MIM](https://github.com/vbti-development/onedl-mim): MIM installs OpenMMLab packages.\n\n## Projects in OpenMMLab\n\n- [MMagic](https://github.com/open-mmlab/mmagic): Open**MM**Lab **A**dvanced, **G**enerative and **I**ntelligent **C**reation toolbox.\n- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.\n- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO series toolbox and benchmark.\n- [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox.\n- [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.\n- [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 3D human parametric model toolbox and benchmark.\n- [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab self-supervised learning toolbox and benchmark.\n- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab model compression toolbox and benchmark.\n- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab fewshot learning toolbox and benchmark.\n- [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark.\n- [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.\n- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark.\n- [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.\n- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox.\n- [MMEval](https://github.com/open-mmlab/mmeval): A unified evaluation library for multiple machine learning libraries.\n- [Playground](https://github.com/open-mmlab/playground): A central hub for gathering and showcasing amazing projects built upon OpenMMLab.\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "OpenMMLab Semantic Segmentation Toolbox and Benchmark",
"version": "1.3.0rc0",
"project_urls": {
"Documentation": "https://onedl-mmsegmentation.readthedocs.io/",
"Homepage": "https://github.com/vbti-development/mmsegmentation",
"Repository": "https://github.com/vbti-development/onedl-mmsegmentation"
},
"split_keywords": [
"computer vision",
" semantic segmentation"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "74ca93a94e0ff32354a33cc9583c476036824577dcbbe8cb4874d17246f07137",
"md5": "ec1f1a8d040e0d0f9c19939691088ed0",
"sha256": "c8bd7ea3f5b4de3e9d8d0c47295db75841daed9ee372eb8649f9b3acc3270257"
},
"downloads": -1,
"filename": "onedl_mmsegmentation-1.3.0rc0.tar.gz",
"has_sig": false,
"md5_digest": "ec1f1a8d040e0d0f9c19939691088ed0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 1805625,
"upload_time": "2025-08-06T12:36:26",
"upload_time_iso_8601": "2025-08-06T12:36:26.324385Z",
"url": "https://files.pythonhosted.org/packages/74/ca/93a94e0ff32354a33cc9583c476036824577dcbbe8cb4874d17246f07137/onedl_mmsegmentation-1.3.0rc0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-06 12:36:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "vbti-development",
"github_project": "mmsegmentation",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"circle": true,
"requirements": [],
"lcname": "onedl-mmsegmentation"
}
JSON
