[WIP] Finetune MAE on Downstream Image Classification Datasets

[zzc98]

Motivation

Fine-tuning MAE in 11 downstream image classification datasets, including Food101, CIFAR10, CIFAR100, SUN397, Stanford Cars, FGVC Aircraft, PASCAL VOC 2007 cls, DTD, Oxford-IIIT Pets, Caltech101, and Oxford 102 Flowers.

BC-breaking (Optional)

Does the modification introduce changes that break the backward compatibility of the downstream repositories?
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

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

Patch coverage: 45.57% and project coverage change: -1.07 ⚠️

Comparison is base (f9dcae2) 68.16% compared to head (c2a226f) 67.09%.

❗ Current head c2a226f differs from pull request most recent head 7dfd991. Consider uploading reports for the commit 7dfd991 to get more accurate results

Additional details and impacted files

@@            Coverage Diff             @@
##              dev    #1624      +/-   ##
==========================================
- Coverage   68.16%   67.09%   -1.07%     
==========================================
  Files         295      308      +13     
  Lines       23372    24573    +1201     
  Branches     3713     3898     +185     
==========================================
+ Hits        15932    16488     +556     
- Misses       6880     7483     +603     
- Partials      560      602      +42     

Flag	Coverage Δ
unittests	67.09% <45.57%> (-1.07%)	⬇️

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

Impacted Files	Coverage Δ
mmpretrain/apis/image_retrieval.py	21.42% <ø> (ø)
mmpretrain/datasets/__init__.py	68.42% <0.00%> (-5.87%)	⬇️
mmpretrain/datasets/gqa_dataset.py	0.00% <0.00%> (ø)
mmpretrain/datasets/nocaps.py	0.00% <0.00%> (ø)
mmpretrain/datasets/scienceqa.py	0.00% <0.00%> (ø)
mmpretrain/datasets/textvqa.py	0.00% <0.00%> (ø)
mmpretrain/models/multimodal/__init__.py	40.00% <0.00%> (-4.45%)	⬇️
...retrain/models/multimodal/chinese_clip/__init__.py	0.00% <0.00%> (ø)
mmpretrain/models/multimodal/chinese_clip/bert.py	0.00% <0.00%> (ø)
...ain/models/multimodal/chinese_clip/chinese_clip.py	0.00% <0.00%> (ø)
... and 28 more

... and 1 file with indirect coverage changes

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