How to build a deepstream pipeline using both nvinfer and nvinferaudio?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

I want to build one deepstream pipeline using both nvinfer (for video inference) and nvinferaudio (for audio inference) and read the same video/rtsp source (including audio). Could you give sample pipeline (ex: pipeline built from gst-launch,…etc) or docs to refer?
Thank you very much.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) 5.1.1
• TensorRT Version 8.6
• Issue Type (questions, new requirements, bugs) questions

3

There is a sample for dGPU in DeepStream SDK dGPU package: /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-avsync

4

Thank you very much,
Is it possible to implement on Jetson?

5

We will consider to add similar sample in Jetson package.

6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.