Performance accessment for my object detection app (DS6 python) from multi rtsp stream

[shaojun]

There’re mutiple cameras in my production scenario, I’m planning to use Jetson NX or higher spec hardware to deploy a custom DS6 python app to implement the object detection for all of the cameras:

• All cameras output 720p or 1080p with h.264 encoding, FPS30 streams by RTSP
  so my DS6 python app needs to read the streams by RTSP.
• My DS6 python app is using a single TAO retrained detectnet_v2 resnet18 model for inference
  so the inferencing is based on single one model.
• Requires inference perf can achive 30FPS

the benchmark cases listed in this repo are all for single stream, I’m not sure how to assess with my case of multiple RTSP stream, Could you help?