export get_simcc_maximum for simcc

[RunningLeon]

Motivation

export get_simcc_maximum for simcc and rtmpose models.

Modification

Support torch2onnx with post-processing get_simcc_maximum for onnxruntime and tensorrt backend.

• Note that ncnn backend is not supported in this PR.

BC-breaking (Optional)

None

Use cases (Optional)

Add the following records to deploy config to enable exporting get_simcc_maximum

codebase_config = dict(
    export_postprocess=True  # export get_simcc_maximum
)

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[codecov]

Codecov Report

Attention: 30 lines in your changes are missing coverage. Please review.

Files	Coverage Δ
mmdeploy/codebase/mmpose/codecs/__init__.py	100.00% <100.00%> (ø)
mmdeploy/codebase/mmpose/models/heads/__init__.py	100.00% <100.00%> (ø)
mmdeploy/codebase/mmpose/deploy/pose_detection.py	72.19% <33.33%> (-0.79%)	⬇️
...loy/codebase/mmpose/deploy/pose_detection_model.py	54.26% <14.28%> (-1.39%)	⬇️
...mdeploy/codebase/mmpose/models/heads/simcc_head.py	37.50% <37.50%> (ø)
mmdeploy/codebase/mmpose/codecs/post_processing.py	14.28% <14.28%> (ø)

📢 Thoughts on this report? Let us know!.

[RunningLeon]

@Tau-J hi, could you take a look at this PR? And may let the user of this request have a try.