[Feature] Add model ensemble tools

[zhijiejia]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Convenient segmentation probability ensemble of multiple models

Modification

Added model_ensemble.py files, added aug_test_logits and simple_test_logits functions, in mmseg/models/segmentors/encoder_decoder.py

BC-breaking (Optional)

Use cases (Optional)

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[CLAassistant]

All committers have signed the CLA.

[codecov]

Codecov Report

Base: 89.09% // Head: 88.97% // Decreases project coverage by -0.11% ⚠️

Coverage data is based on head (8836c44) compared to base (04afdb3).
Patch coverage: 14.28% of modified lines in pull request are covered.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #2218      +/-   ##
==========================================
- Coverage   89.09%   88.97%   -0.12%     
==========================================
  Files         145      145              
  Lines        8721     8735      +14     
  Branches     1472     1473       +1     
==========================================
+ Hits         7770     7772       +2     
- Misses        708      720      +12     
  Partials      243      243              

Flag	Coverage Δ
unittests	88.97% <14.28%> (-0.12%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmseg/models/segmentors/encoder_decoder.py	83.04% <14.28%> (-6.14%)	⬇️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

[MeowZheng]

It looks good to me.

There is the last requirement that please add instructions in https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/useful_tools.md

and its Chinese version
https://github.com/open-mmlab/mmsegmentation/blob/master/docs/zh_cn/useful_tools.md

[zhijiejia]

It looks good to me.

There is the last requirement that please add instructions in https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/useful_tools.md

and its Chinese version https://github.com/open-mmlab/mmsegmentation/blob/master/docs/zh_cn/useful_tools.md

Thanks your help, I have added the zh_cn and en instruction in docs/zh_cn/useful_tools.md and docs/en/useful_tools.md

[jason102811]

zhijiejia，您好！您在MMSeg项目中给我们提的PR非常重要，感谢您付出私人时间帮助改进开源项目，相信很多开发者会从你的PR中受益。
我们非常期待与您继续合作，OpenMMLab专门成立了贡献者组织MMSIG，为贡献者们提供开源证书、荣誉体系和专享好礼，可通过添加微信：openmmlabwx 联系我们（请备注mmsig+GitHub id），由衷希望您能加入！
Dear zhijiejia,
First of all, we want to express our gratitude for your significant PR in the MMSeg project. Your contribution is highly appreciated, and we are grateful for your efforts in helping improve this open-source project during your personal time. We believe that many developers will benefit from your PR.
We are looking forward to continuing our collaboration with you. OpenMMLab has established a special contributors' organization called MMSIG, which provides contributors with open-source certificates, a recognition system, and exclusive rewards. You can contact us by adding our WeChat（if you have WeChat): openmmlabwx, or join in our discord： https://discord.gg/qH9fysxPDW. We sincerely hope you will join us!
Best regards！ @zhijiejia