I run sound classification sample app (in /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream-audio folder) and object detection sample app (in /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream-app folder) successfully. Now, I want to integrate both of them to one pipeline to run in parallel (using a config file, read the same video source, and output to the same OSD), Is it possible to do that? If possible, Could you give me a design/tutorials?
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
The sample /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream-avsync is a pipeline to run audio inferencing and video inferencing in one pipeline. Please read the /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream-avsync/README carefully before you try the sample.
Thank you for your answer.
I checked deepstream-avsync app in /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/ folder but I cannot find it (both my Jetson AGX Xavier and Jetson Orin nano boards). I flashed Jetpack4.6 and Jetpack5.1 for two boards above.
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
No. The model is not supported in Jetson. You can refer to the pipeline.