[Feature] EfficientNets NoisyStudent & L2

[okotaku]

Motivation

Related issue: #1107

Modification

Add l2-arch.
Add l2 convert script.
Add noisy student weights.
improve the model page
update the flops

Use cases (Convert)

wget https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/noisystudent/noisy_student_efficientnet-b0.tar.gz
tar -xf noisy_student_efficientnet-b0.tar.gz
python3 tools/model_converters/efficientnet_to_mmcls.py noisy_student_efficientnet-b0/model.ckpt noisy_student_efficientnet-b0.pth

# for l2
wget https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/noisystudent/noisy_student_efficientnet-l2.tar.gz
tar -xf noisy_student_efficientnet-l2.tar.gz
python3 tools/model_converters/efficientnet_to_mmcls.py noisy_student_efficientnet-l2/model.ckpt noisy_student_efficientnet-l2.pth --l2

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: 91.31% // Increases project coverage by +91.29% 🎉

Coverage data is based on head (bce907a) compared to base (b8b31e9).
Patch has no changes to coverable lines.

Additional details and impacted files

@@             Coverage Diff              @@
##           dev-1.x    #1122       +/-   ##
============================================
+ Coverage     0.02%   91.31%   +91.29%     
============================================
  Files          121      136       +15     
  Lines         8217     9986     +1769     
  Branches      1368     1577      +209     
============================================
+ Hits             2     9119     +9117     
+ Misses        8215      658     -7557     
- Partials         0      209      +209     

Flag	Coverage Δ
unittests	91.31% <ø> (+91.29%)	⬆️

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

Impacted Files	Coverage Δ
mmcls/apis/inference.py	0.00% <0.00%> (ø)
mmcls/datasets/transforms/compose.py
mmcls/models/heads/arcface_head.py	85.48% <0.00%> (ø)
mmcls/models/retrievers/__init__.py	100.00% <0.00%> (ø)
mmcls/models/backbones/swin_transformer_v2.py	89.47% <0.00%> (ø)
mmcls/models/backbones/deit3.py	94.52% <0.00%> (ø)
mmcls/structures/utils.py	77.77% <0.00%> (ø)
mmcls/models/utils/layer_scale.py	86.66% <0.00%> (ø)
mmcls/models/backbones/edgenext.py	95.20% <0.00%> (ø)
mmcls/models/retrievers/base.py	100.00% <0.00%> (ø)
... and 126 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.

[Ezra-Yu]

LGTM.