Assistance Needed: Unable to Access poseclassificationnet Output in DeepStream Pose Classification App

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hello everyone,

I’m currently working with the DeepStream Pose Classification app, which utilizes three models. I can easily access the outputs of the first two models, but I’m having difficulty locating the output for the third model, poseclassificationnet, in the C++ code.

I’ve thoroughly explored the code but haven’t found where or how poseclassificationnet’s results are handled or accessed. If anyone has insights or experience with this app, I would greatly appreciate guidance on how to retrieve or locate the output for this specific model.

Here’s the repository I’m using:

Thanks in advance!

3

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)

• DeepStream Version

• JetPack Version (valid for Jetson only)

• TensorRT Version

• NVIDIA GPU Driver Version (valid for GPU only)

• Issue Type( questions, new requirements, bugs)

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

4

Hardware Platform: Jetson AGX Orin
DeepStream Version: 7.0
JetPack Version: 6
TensorRT Version: 8.6.2
CUDA Version: 12.2
Description:
I’m currently working with the DeepStream Pose Classification app from the DeepStream TAO Apps repository, which uses three models:

  1. PeopleNet
  2. BodyPose3D
  3. PoseClassificationNet

I can easily access the outputs of PeopleNet and BodyPose3D, but I’m struggling to locate the output handling for PoseClassificationNet in the C++ code. Despite thoroughly exploring the codebase, I haven’t been able to identify where or how the results from poseclassificationnet are processed or accessed.
If anyone has experience with this app or insights into how to retrieve the output for poseclassificationnet, I would appreciate any guidance on:

  • Where in the code the poseclassificationnet output is handled
  • How to access or log the output for this model
5

please refer to this code.

6

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

7

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