How do I customize nvinfer output in DeepStream

Hi,everyone

I trained a model , it output layer contains face detection bbox, face key points , face quality
I checked the docs Gst-nvinfer API ,Didn’t find the answer
output layer :
face detection bbox (left,top,width,height,confidence) (draw rect)
face key points (x1,y1,x2,y2,x3,y3,x4,y4,x5,y5) (draw circles)
quality (0-1) (draw text)

I how to codeing post-process in deepstream like yolov4 post-process in deepstream , and sent it to nvosd

Thanks

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

• Hardware Platform :GPU
• DeepStream Version :5.1
• TensorRT Version:7.2
• language: python3.6
• camera IP: Hikvision

this is new requirement for nvinfer in deepstream

I train a model , output layer contains bboxes, key points , img quality

face detection bbox (left,top,width,height,confidence) (draw rect)
face key points (x1,y1,x2,y2,x3,y3,x4,y4,x5,y5) (draw circles)
quality (0-1) (draw text)

how to codeing post-process of model for parse func in deepstream ?

Please refer the README.md

yolov4_deepstream/deepstream_yolov4 at master · NVIDIA-AI-IOT/yolov4_deepstream · GitHub