Multiple sources for deepstream pose-classification

[edit_or]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) RTX3080
• DeepStream Version 6.3
Since deepstream-6.3’s poseclassification, I am thinking to use GRPC approach.
Can I run multiple sources using Triton inference server and GRPC config file?

[fanzh]

the sample has already supported triton CAPI and GRPC mode. please refer to configs/app/deepstream_pose_classification_config.yaml.

[edit_or]

So does it support multi cctvs?

[fanzh]

this sample uses a uridecodebin so that any type of input (e.g. RTSP/File), any GStreamer
supported container format, and any codec can be used as input. please refer to /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3’s reamde for how to set uri.
you can modify uri in configs/app/deepstream_pose_classification_config.yaml.

[edit_or]

Thank you

[fanzh]

Sorry for the late reply, Is this still an DeepStream issue to support? Thanks!

[edit_or]

thanks