mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
32 Commits
9 Branches
47 Tags
759 MiB
Python 98.9%
Shell 0.9%
Dockerfile 0.2%
 
 
 
Go to file
Han Hu 8ff866d60c
Add "disentangled non-local (DNL) neural networks" [ECCV2020] (#37) 
* Add DNLHead

* add configs

* add weight decay mult

* add norm back

* Update README.md

* matched inference performance

* Fixed shape

* sep conv_out

* no norm

* add norm back

* complete model zoo

* add tests

* Add test forward

* Add more test

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
 		2020-09-07 16:22:00 +08:00
.dev init commit 2020-07-10 02:39:01 +08:00
.github Add pytorch 1.6 CI (#64) 2020-08-12 18:55:40 +08:00
configs Add "disentangled non-local (DNL) neural networks" [ECCV2020] (#37) 2020-09-07 16:22:00 +08:00
demo Add Colab Tutorial (#7) 2020-07-10 16:55:47 +08:00
docker Add Colab Tutorial (#7) 2020-07-10 16:55:47 +08:00
docs Windows Support (Experimental) (#75) 2020-08-28 11:34:44 +08:00
mmseg Add "disentangled non-local (DNL) neural networks" [ECCV2020] (#37) 2020-09-07 16:22:00 +08:00
requirements Add pypi deployment (#11) 2020-07-13 20:54:32 +08:00
resources init commit 2020-07-10 02:39:01 +08:00
tests Add "disentangled non-local (DNL) neural networks" [ECCV2020] (#37) 2020-09-07 16:22:00 +08:00
tools Onnx upsample (#100) 2020-09-03 19:59:13 +08:00
.gitignore Auto get version info and git hash (#55) 2020-08-11 19:23:35 +08:00
.pre-commit-config.yaml init commit 2020-07-10 02:39:01 +08:00
.readthedocs.yml Add Colab Tutorial (#7) 2020-07-10 16:55:47 +08:00
LICENSE init commit 2020-07-10 02:39:01 +08:00
README.md Add "disentangled non-local (DNL) neural networks" [ECCV2020] (#37) 2020-09-07 16:22:00 +08:00
pytest.ini init commit 2020-07-10 02:39:01 +08:00
requirements.txt Add pypi deployment (#11) 2020-07-13 20:54:32 +08:00
setup.cfg add pytorch2onnx part (#12) 2020-08-14 03:28:21 +08:00
setup.py Auto get version info and git hash (#55) 2020-08-11 19:23:35 +08:00

README.md


PyPI docs badge codecov license

Documentation: https://mmsegmentation.readthedocs.io/

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 to 1.5.

demo image

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

v0.5.1 was released in 11/08/2020. 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:

Supported methods:

Installation

Please refer to INSTALL.md for installation and dataset preparation.

Get Started

Please see getting_started.md for the basic usage of MMSegmentation. There are also tutorials for adding new dataset, designing data pipeline, and adding new modules.

A Colab tutorial is also provided. You may preview the notebook here or directly run on Colab.

Contributing

We appreciate all contributions to improve MMSegmentation. Please refer to 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.