[Feature] Support RTMDet and RTMPose ncnn deployment

[hanrui1sensetime]

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

Motivation

Support RTMDet and RTMPose ncnn deployment

Modification

• Add rewriter for rtmpose_block.
• Add configs.

BC-breaking (Optional)

None.

Use cases (Optional)

None.

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.

[grimoire]

visualize failed with

2023-03-16:11:32:18 - root - ERROR - not enough values to unpack (expected 2, got 1)
Traceback (most recent call last):
  File "/home/user/space/repo2.0/mmdeploy/mmdeploy/utils/utils.py", line 41, in target_wrapper
    result = target(*args, **kwargs)
  File "/home/user/space/repo2.0/mmdeploy/mmdeploy/apis/visualize.py", line 72, in visualize_model
    result = model.test_step(model_inputs)[0]
  File "/home/user/space/repo2.0/mmengine/mmengine/model/base_model/base_model.py", line 145, in test_step
    return self._run_forward(data, mode='predict')  # type: ignore
  File "/home/user/space/repo2.0/mmengine/mmengine/model/base_model/base_model.py", line 326, in _run_forward
    results = self(**data, mode=mode)
  File "/home/user/anaconda3/envs/repo2.0/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/user/space/repo2.0/mmdeploy/mmdeploy/codebase/mmpose/deploy/pose_detection_model.py", line 104, in forward
    batch_pred_x, batch_pred_y = batch_outputs
ValueError: not enough values to unpack (expected 2, got 1)

[hanrui1sensetime]

visualize failed with

2023-03-16:11:32:18 - root - ERROR - not enough values to unpack (expected 2, got 1)
Traceback (most recent call last):
  File "/home/user/space/repo2.0/mmdeploy/mmdeploy/utils/utils.py", line 41, in target_wrapper
    result = target(*args, **kwargs)
  File "/home/user/space/repo2.0/mmdeploy/mmdeploy/apis/visualize.py", line 72, in visualize_model
    result = model.test_step(model_inputs)[0]
  File "/home/user/space/repo2.0/mmengine/mmengine/model/base_model/base_model.py", line 145, in test_step
    return self._run_forward(data, mode='predict')  # type: ignore
  File "/home/user/space/repo2.0/mmengine/mmengine/model/base_model/base_model.py", line 326, in _run_forward
    results = self(**data, mode=mode)
  File "/home/user/anaconda3/envs/repo2.0/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/user/space/repo2.0/mmdeploy/mmdeploy/codebase/mmpose/deploy/pose_detection_model.py", line 104, in forward
    batch_pred_x, batch_pred_y = batch_outputs
ValueError: not enough values to unpack (expected 2, got 1)

Should use pose-detection_simcc_ncnn_static-256x192.py as deploy config.

[grimoire]

LGTM

[AllentDan]

The .cpp files need to be clang-formatted.

[hanrui1sensetime]

The .cpp files need to be clang-formatted.

Will be formatted in another PR.