How to run facial embeeding model with DeepStream

I came across this model on ngc NVIDIA NGC
It says to parse the embeddings, a custom parser is required.

Can anyone please give some pointers on how this should be approached or if there is a parser already available.
I want to integrate this model with deepstream pipeline to get the facial embeddings and correct the face pose for other tasks.

Can I integrate it with DeepStream 5.1 ?


Where did you find the comment ?

Deployment Files

The following files are required to run each TAO model with Deepstream:

  • ds_tlt.c : The application main file
  • nvdsinfer_custombboxparser_tlt : A custom parser function on infernece end nodes
  • Models: TAO models from NGC
  • Model configuration files: The Deepstream Inference configuration file

For deploying fpe model with deepstream, please refer to deepstream_tao_apps/apps/tao_others/deepstream-faciallandmark-app at release/tao3.0 · NVIDIA-AI-IOT/deepstream_tao_apps · GitHub
DS 6.0 or above is needed.