[Feature] Add inferencers

[Ben-Louis]

Motivation

Modification

1. add Pose2DInferencer which can conduct 2D pose estimation on image/video/webcam with top-down/bottom-up models
2. add an inference wrapper MMPoseInferencer
3. add demo script to run inferencer
4. add unittest for inferences
5. add document about inferences

Usage

1. Images
   python demo/inferencer_demo.py tests/data/coco/ --pose2d human --show --pred-out-dir predictions
2. Webcam
   python demo/inferencer_demo.py webcam --pose2d human --vis-out-dir visualization

BC-breaking (Optional)

Use cases (Optional)

Checklist

Before PR:

• I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
• Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
• Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
• New functionalities are covered by complete unit tests. If not, please add more unit tests to ensure correctness.
• The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

• CLA has been signed and all committers have signed the CLA in this PR.

[codecov]

Codecov Report

Base: 80.17% // Head: 82.15% // Increases project coverage by +1.97% 🎉

Coverage data is based on head (3a7a099) compared to base (0b7abbc).
Patch coverage: 83.50% of modified lines in pull request are covered.

❗ Current head 3a7a099 differs from pull request most recent head d80851c. Consider uploading reports for the commit d80851c to get more accurate results

Additional details and impacted files

@@             Coverage Diff             @@
##           dev-1.x    #1969      +/-   ##
===========================================
+ Coverage    80.17%   82.15%   +1.97%     
===========================================
  Files          210      220      +10     
  Lines        12521    13100     +579     
  Branches      2112     2227     +115     
===========================================
+ Hits         10039    10762     +723     
+ Misses        2026     1842     -184     
- Partials       456      496      +40     

Flag	Coverage Δ
unittests	82.15% <83.50%> (+1.97%)	⬆️

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

Impacted Files	Coverage Δ
mmpose/visualization/local_visualizer.py	79.66% <60.00%> (-1.18%)	⬇️
mmpose/apis/inferencers/base_mmpose_inferencer.py	71.34% <71.34%> (ø)
mmpose/datasets/transforms/bottomup_transforms.py	79.77% <75.00%> (-0.11%)	⬇️
mmpose/apis/inferencers/mmpose_inferencer.py	75.30% <75.30%> (ø)
mmpose/apis/inferencers/pose2d_inferencer.py	75.72% <75.72%> (ø)
mmpose/models/heads/heatmap_heads/cid_head.py	80.45% <80.45%> (ø)
mmpose/models/utils/transformer.py	82.40% <87.50%> (+8.28%)	⬆️
mmpose/codecs/decoupled_heatmap.py	88.42% <88.42%> (ø)
mmpose/codecs/utils/instance_property.py	89.18% <89.18%> (ø)
mmpose/codecs/utils/gaussian_heatmap.py	86.02% <90.00%> (+0.46%)	⬆️
... and 29 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.