How should I calculate the fps when I pull 16 streams together using deepstream

[13713996904]

• Hardware Platform (Jetson / GPU)
x86-64 Ubuntu 20.04 LTS machine with Geforce GTX 3060
• DeepStream Version
6.1.0
• TensorRT Version
8.2.5.1
• NVIDIA GPU Driver Version (valid for GPU only)
515.48.07
• Issue Type( questions, new requirements, bugs)
I tested deepstream refering https://github.com/NVIDIA-AI-IOT/yolo_deepstream/tree/main/deepstream_yolo, the performance table show that fps of 16 streams is much faster than 1 streams. I am confused with the performance evaluation,how should I calculate the fps when I pull 16 streams together using deepstream, the fps is the overall fps of 16 streams or just single one of them. when I pull one stream using deepstream, the fps is 255, when I pull 16 streams together, the fps of every single stream is just 24, is that reasonable?

[yuweiw]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

How did you get this fps currently? You can try to adjust the batch-size of nvstreammux to improve the preformance.