Support CSRA head.

[JiayuXu0]

Motivation

CSRA github
CSRA paper

Modification

Add CSRA multi-label head and test case.

Usage

python ./tools/train.py ./configs/csra/resnet101_csra_1xb16_voc07_448.py

Checklist

Before PR:

• Pre-commit or other linting tools are used to fix the potential lint issues.
• Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
• The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
• The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

• If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects, like MMDet or MMSeg.
• CLA has been signed and all committers have signed the CLA in this PR.

[CLAassistant]

All committers have signed the CLA.

[Ezra-Yu]

Have you run experiments in the VOC2007 dataset?

[JiayuXu0]

Have you run experiments in the VOC2007 dataset?

Thanks for your suggestion. I have added the experiments in the pull requests.

[codecov]

Codecov Report

Merging #881 (31dbe12) into dev (b5bb86a) will increase coverage by 0.00%.
The diff coverage is 84.74%.

❗ Current head 31dbe12 differs from pull request most recent head b8655f5. Consider uploading reports for the commit b8655f5 to get more accurate results

@@           Coverage Diff           @@
##              dev     #881   +/-   ##
=======================================
  Coverage   85.86%   85.86%           
=======================================
  Files         136      137    +1     
  Lines        9306     9363   +57     
  Branches     1611     1621   +10     
=======================================
+ Hits         7991     8040   +49     
- Misses       1076     1082    +6     
- Partials      239      241    +2     

Flag	Coverage Δ
unittests	85.79% <84.74%> (+<0.01%)	⬆️

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

Impacted Files	Coverage Δ
mmcls/datasets/voc.py	31.81% <28.57%> (-1.52%)	⬇️
mmcls/models/heads/multi_label_csra_head.py	92.15% <92.15%> (ø)
mmcls/models/heads/__init__.py	100.00% <100.00%> (ø)

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

[JiayuXu0]

Have you run experiments in the VOC2007 dataset?

I use pre-commit hook that checks and formats codes. So re-summit codes for review. Thanks.

[JiayuXu0]

1. Add CSRA config and README.md.
2. Unified processing method with MultiLabelLinearClsHead for difficult label.

[Ezra-Yu]

LGTM.

[OpenMMLab-Assistant005]

Hi @JiayuXu0 ！First of all, we want to express our gratitude for your significant PR in the MMCls 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 would also like to invite you to join our Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. Look forward to seeing you there! Join us ：https://discord.gg/UjgXkPWNqA

If you have WeChat account，welcome to join our community on WeChat. You can add our assistant ：openmmlabwx. Please add "mmsig + Github ID" as a remark when adding friends：）
Thank you again for your contribution❤