Issue Retrieving BodyPose3DNet Metadata in Graph Composer

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Environment Details:
• Hardware Platform (Jetson / GPU) : dGPU (x86_64)
• DeepStream Version : 7.1
• JetPack Version (valid for Jetson only) : N/A
• TensorRT Version : 10.3.0.26
• NVIDIA GPU Driver Version : 560.35.05
• Issue Type : Question

Hello, I’m trying to implement the BodyPose3D example in Graph Composer. So far, the pipeline runs without any issues, but I can’t be sure if BodyPose3DNet is actually working.

sc-1
sc-11479×934 92.8 KB

When I try to retrieve the metadata from the model using nvdsmsgconvbroker node, only the metadata from the PeopleNet model is sent.

Could you provide guidance on how to verify that BodyPose3DNet is generating metadata and ensure it is properly included in the output? Are there any specific settings required for nvdsmsgconvbroker to process multiple models’ metadata?

Any help would be greatly appreciated.

3

The published extentions are for people and vehicles information only. It is hard to customize the message in extension level. You may try Difficulty Saving Inference Results or Metadata to a File in Graph Composer - #5 by Fiona.Chen