[Feature] Support ConvNeXt-V2 backbone.

[mzr1996]

Modification

• Add ConvNeXt-V2 backbone
• Fix the wrong usage of the registry of mmengine.

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.

[codecov]

Codecov Report

Base: 0.02% // Head: 88.61% // Increases project coverage by +88.58% 🎉

Coverage data is based on head (bf1ed51) compared to base (b8b31e9).
Patch has no changes to coverable lines.

Additional details and impacted files

@@             Coverage Diff              @@
##           dev-1.x    #1294       +/-   ##
============================================
+ Coverage     0.02%   88.61%   +88.58%     
============================================
  Files          121      161       +40     
  Lines         8217    12679     +4462     
  Branches      1368     2034      +666     
============================================
+ Hits             2    11235    +11233     
+ Misses        8215     1106     -7109     
- Partials         0      338      +338     

Flag	Coverage Δ
unittests	88.61% <ø> (+88.58%)	⬆️

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

Impacted Files	Coverage Δ
mmcls/datasets/transforms/compose.py
mmcls/models/retrievers/base.py	100.00% <0.00%> (ø)
mmcls/models/utils/layer_scale.py	86.66% <0.00%> (ø)
mmcls/models/utils/norm.py	80.00% <0.00%> (ø)
mmcls/models/heads/multi_label_csra_head.py	40.54% <0.00%> (ø)
mmcls/models/backbones/davit.py	84.94% <0.00%> (ø)
mmcls/models/backbones/deit3.py	94.52% <0.00%> (ø)
mmcls/evaluation/metrics/voc_multi_label.py	100.00% <0.00%> (ø)
mmcls/models/backbones/efficientnet_v2.py	96.03% <0.00%> (ø)
mmcls/models/backbones/mobilevit.py	91.15% <0.00%> (ø)
... and 152 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.

[yingfhu]

Should there be another pull request to change the usage of build_activation_layer and build_norm_layer in all models?

The code LGTM, please add some docs and UT

[austinmw]

Hi, will the ConvNeXt-V2 implementation be able to be trained with MMSelfSup?