CodeCamp #150 [Feature] Add ISNet

[unrealMJ]

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

Support ISNet.
paper link: ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

Modification

Add ISNet decoder head.
Add ISNet config.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

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.

[xiexinch]

Hi @unrealMJ,
Thanks for your contribution, please fix the lint error. You might refer to our Contribution Guide.

[codecov]

Codecov Report

Base: 83.41% // Head: 82.59% // Decreases project coverage by -0.81% ⚠️

Coverage data is based on head (f7f5b7a) compared to base (6af2b8e).
Patch coverage: 22.77% of modified lines in pull request are covered.

❗ Current head f7f5b7a differs from pull request most recent head 71a6331. Consider uploading reports for the commit 71a6331 to get more accurate results

Additional details and impacted files

@@             Coverage Diff             @@
##           dev-1.x    #2400      +/-   ##
===========================================
- Coverage    83.41%   82.59%   -0.82%     
===========================================
  Files          144      144              
  Lines         8375     8228     -147     
  Branches      1249     1223      -26     
===========================================
- Hits          6986     6796     -190     
- Misses        1183     1243      +60     
+ Partials       206      189      -17     

Flag	Coverage Δ
unittests	82.59% <22.77%> (-0.82%)	⬇️

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

Impacted Files	Coverage Δ
mmseg/models/decode_heads/isnet_head.py	22.00% <22.00%> (ø)
mmseg/models/decode_heads/__init__.py	100.00% <100.00%> (ø)
mmseg/models/backbones/timm_backbone.py	45.83% <0.00%> (-37.51%)	⬇️
mmseg/models/segmentors/base.py	87.87% <0.00%> (-1.36%)	⬇️
mmseg/models/decode_heads/mask2former_head.py	89.65% <0.00%> (-0.18%)	⬇️
mmseg/models/decode_heads/maskformer_head.py	93.75% <0.00%> (-0.10%)	⬇️
mmseg/datasets/__init__.py	100.00% <0.00%> (ø)
mmseg/models/segmentors/__init__.py	100.00% <0.00%> (ø)
mmseg/datasets/transforms/__init__.py	100.00% <0.00%> (ø)
mmseg/models/segmentors/seg_tta.py
... and 4 more

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.

[xiexinch]

We might move these codes to the projects folder and should add README.md.

#2412