AMB82 SCRFD Convert To ONNX

SCRFD

SCRFD is an efficient high accuracy face detection approach which is initialy described in Arxiv.
It provides an easy-to-use pipeline to train high efficiency face detectors with NAS supporting.
You can visit [InsignFace](https://github.com/deepinsight/insightface/tree/master/detection/scrfd) to get more information.
For amebaPro2 edge computing, I suggest makers use [SCRFD_500M_KPS](https://1drv.ms/u/s!AswpsDO2toNKri_NDM0GIkPpkE2f?e=JkebJo).

Set Environment for SCRFD

The default format of SCRFD is pytorch, so it has to be converted to ONNX format:

cd ~/insightface/detection/scrfd

python tools/scrfd2onnx.py configs/scrfd/scrfd_500m_bnkps.py scrfd_500mkps.pt --shape 640 640

You can fine tools/scrfd2onnx.py in [InsignFace](https://github.com/deepinsight/insightface/tree/master/detection/scrfd).

If Makers encounter Python package dependency issues, they can try creating isolated Python environments with virtualenv and referring to our requirements_scrfd.txt to install Python packages.

pip install -r requirements_scrfd.txt

In order to show you how to translate and export SCRFD quickly, we can download the pretrained weights from Internet:
[scrfd.lite.ai.toolkit](https://github.com/DefTruth/scrfd.lite.ai.toolkit)
Please download `scrfd_500m_bnkps_shape640x640.onnx` or `scrfd_500m_bnkps_shape320x320.onnx ` for amebaPro2 edge computing.

Download