Is there a way to use secondary_gie_bin without setting up C application?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) RTX2080
• DeepStream Version 5.0-dp
• TensorRT Version 7.0.0.11
• NVIDIA GPU Driver Version (valid for GPU only) 440.64.00

I’m trying to concurrently run multiple nvinfer elements in secondary mode and I’d like to use pipeline architecture similar to secondary_gie_bin from Deepstream samples. But my GStreamer application gets started from python code, so, as far as I understand, I cannot use the factory method create_secondary_gie_bin.

Is there a way to use secondary_gie_bin as a standalone element (for example, from dynamically loadable plugin library)? Are there plans to provide element with this functionality?

3

May I know what your scenario is. You can refer DS test2 python sample - it can help with secondary gie