[Enhance] Add hparams argument in AutoAugment and RandAugment and some other improvement.

[mzr1996]

Motivation

In AutoAugment and RandAugment, there are many common arguments in sub-policies. Now we have to set these arguments one by one.

Modification

1. Add hparams argument in AutoAugment and RandAugment, so that we can specify common arguments by once.
2. Use hparams and base variable to simplify RandAug settings in swin-transformer.
3. Now pad_val supports using Sequence instead of only tuple.
4. Use smaller test images to speed up unit tests.

BC-breaking (Optional)

No.

Use cases (Optional)

>>> policies = [
...     dict(
...         type='Translate',
...         magnitude_key='magnitude',
...         magnitude_range=(0, 1),
...         pad_val=128,
...         direction='horizontal'),
...     dict(
...         type='Rotate',
...         magnitude_key='angle',
...         magnitude_range=(0, 90))
... ]
>>> t = RandAugment(
...       policies=policies, 
...       num_policies=2, 
...       magnititude_level=12, 
...       hparams=dict(pad_val=15))
>>> # hparams won't override setting in policies config
>>> t.policies[0]['pad_val']
128
>>> # use hparams if not set in policies config
>>> t.policies[1]['pad_val']
15

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

Merging #398 (83ee8f8) into master (a747458) will increase coverage by 0.21%.
The diff coverage is 90.62%.

@@            Coverage Diff             @@
##           master     #398      +/-   ##
==========================================
+ Coverage   76.51%   76.72%   +0.21%     
==========================================
  Files          97       97              
  Lines        5224     5238      +14     
  Branches      856      861       +5     
==========================================
+ Hits         3997     4019      +22     
+ Misses       1108     1098      -10     
- Partials      119      121       +2     

Flag	Coverage Δ
unittests	76.72% <90.62%> (+0.21%)	⬆️

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

Impacted Files	Coverage Δ
mmcls/datasets/pipelines/auto_augment.py	79.13% <90.62%> (+0.35%)	⬆️
mmcls/models/heads/linear_head.py	82.60% <0.00%> (-3.60%)	⬇️
mmcls/models/heads/vision_transformer_head.py	91.89% <0.00%> (-1.14%)	⬇️
mmcls/models/heads/multi_label_head.py	64.70% <0.00%> (-0.92%)	⬇️
mmcls/models/heads/stacked_head.py	96.92% <0.00%> (-0.18%)	⬇️
mmcls/apis/test.py	24.13% <0.00%> (ø)
mmcls/apis/train.py	22.72% <0.00%> (ø)
mmcls/datasets/voc.py	38.46% <0.00%> (ø)
mmcls/utils/logger.py	75.00% <0.00%> (ø)
... and 87 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update a747458...83ee8f8. Read the comment docs.

[Ezra-Yu]

Do we need to provide auto_aug configuration file similar to rand_aug.py?

[mzr1996]

Do we need to provide auto_aug configuration file similar to rand_aug.py?

AutoAugment configuration will be added in ViT(#395)

[Ezra-Yu]

LGTM