In the previous

Follow the introduction of MMSegmentation, you can install this project and get start.

Now we use segmentation models as salient detection models to support salient detection.

If you have any questions, please make issues or contact us by any means.

As we are beginners, there may be some problems in this project. Most welcome to correct us.

Thanks very much for your participation.

Installation

Following the mmsegmetation Installation

Get Started

Following the mmsegmetation Get Started.

If you train or test SOD Model, config file uses configs/sod_model/model_duts.py.

If you want to train or test your own models on other datasets, you need to change your own config, and set other model configs and other datasets configs.

You can follow previous configs.

Changes !!!!!

• 2021/01/22:

  Update mmseg/models/segmentors/sod_encoder_decoder.py : base on encoder_decoder.py, support base structure of salient detection encoder2decoder.

  Update mmseg/datasets/sod.py : base custom.py, a base sod datasets process.

  Update mmseg/models/losses/bce_loss.py : support BCELoss and BCE Logits Loss.

  Update mmseg/core/evaluation/sod_eval.py : add F-measure(F-measure, P, R), P_R(Precision-recall data, AP, max F-measure), MAE(mae)

  Update configs/base/datasets : add SOD datasets configs

  Update configs/base/schedules : add SOD schedule configs

  Update configs/ : add some models configs, base configs/base/

• 2021/01/23:

  Update configs/base/datasets/duts.py: add random crop and padding.

• 2021/01/29:

  Update sod_eval.py, debug

MMSegmentation README.md:

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 1.6.

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

v0.10.0 was released in 01/01/2021. 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
• ResNeXt
• HRNet
• ResNeSt
• MobileNetV2
• MobileNetV3

Supported methods:

• FCN
• PSPNet
• DeepLabV3
• PSANet
• DeepLabV3+
• UPerNet
• NonLocal Net
• EncNet
• CCNet
• DANet
• APCNet
• GCNet
• DMNet
• ANN
• OCRNet
• Fast-SCNN
• Semantic FPN
• PointRend
• EMANet
• DNLNet
• CGNet
• Mixed Precision (FP16) Training

Installation

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

Get Started

Please see train.md and inference.md for the basic usage of MMSegmentation. There are also tutorials for customizing dataset, designing data pipeline, customizing modules, and customizing runtime. We also provide many training tricks.

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

Citation

If you find this project useful in your research, please consider cite:

@misc{mmseg2020,
    title={MMSegmentation, an Open Source Semantic Segmentation Toolbox},
    author={MMSegmentation Contributors},
    howpublished = {\url{https://github.com/open-mmlab/mmsegmentation}},
    year={2020}
}

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.

Projects in OpenMMLab

• MMCV: OpenMMLab foundational library for computer vision.
• MMClassification: OpenMMLab image classification toolbox and benchmark.
• MMDetection: OpenMMLab detection toolbox and benchmark.
• MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
• MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
• MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
• MMTracking: OpenMMLab video perception toolbox and benchmark.
• MMPose: OpenMMLab pose estimation toolbox and benchmark.
• MMEditing: OpenMMLab image and video editing toolbox.