[Feature] support MaskFeat pre-training with video

[fangyixiao18]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Prerequisite PR: open-mmlab/mmaction2#2186
Support MaskFeat video pretraining in projects

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

Base: 80.64% // Head: 80.64% // Decreases project coverage by -0.01% ⚠️

Coverage data is based on head (be2d44a) compared to base (408377a).
Patch coverage: 80.48% of modified lines in pull request are covered.

❗ Current head be2d44a differs from pull request most recent head 34d5403. Consider uploading reports for the commit 34d5403 to get more accurate results

Additional details and impacted files

@@             Coverage Diff             @@
##           dev-1.x     #678      +/-   ##
===========================================
- Coverage    80.64%   80.64%   -0.01%     
===========================================
  Files          141      141              
  Lines         5089     5124      +35     
  Branches       671      685      +14     
===========================================
+ Hits          4104     4132      +28     
- Misses         850      854       +4     
- Partials       135      138       +3     

Flag	Coverage Δ
unittests	80.64% <80.48%> (-0.01%)	⬇️

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

Impacted Files	Coverage Δ
mmselfsup/models/utils/__init__.py	100.00% <ø> (ø)
mmselfsup/models/utils/data_preprocessor.py	87.36% <75.75%> (-6.29%)	⬇️
mmselfsup/datasets/transforms/formatting.py	95.31% <100.00%> (+0.23%)	⬆️
...mselfsup/models/target_generators/hog_generator.py	95.45% <100.00%> (ø)
mmselfsup/datasets/transforms/processing.py	89.43% <0.00%> (+0.21%)	⬆️

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.

[YuanLiuuuuuu]

This config file seems redundant

[fangyixiao18]

modified this config for 8 gpus, inherited from the other one

[tonysy]

LGTM(please update the doc with usage of train.py/test.py)