Add onnx runtime inference on pose model

[lucasjinreal]

Add onnx runtime inference on lightweight pose model. This enables more simplier inference and faster speed on CPU compare with Pytorch. More importantly, onnx make all inference code much more simpler and don't require original repo as dependencies. The onnx export can be get from:

https://github.com/jinfagang/lightweight-human-pose-estimation.pytorch

[facebook-github-bot]

Hi @jinfagang!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@fb.com. Thanks!

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[lucasjinreal]

@penincillin Can u take a look at this PR. I added onnx inference on human-pose-estimation, what's more, I also added onnx export for HMR model.

In terms of HRM, on CPU, onnxruntime runs faster than Pytorch even more, 70ms vs 90ms.

And the inference code much more simplifier. which can be easily used for deployment or some other useful scenarios such as VTuber etc.

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!