Implementing face embedding model as secondary gie

[sharma.rahul98912]

• Hardware Platform Nvidia Tesla T4
• DeepStream Version 5.1

• TensorRT Version 7.2.2.3
• NVIDIA GPU Driver Version (valid for GPU only) 460.32…03
• Issue Type( questions, new requirements, bugs) question

Hi, i have model that just outputs 512 floating values as face embeddings.

How can i use that as secondary gie? Also as it does not gives any bbox, how can i get the output in gst-dsexample plugin.

Thanks.

[Fiona.Chen]

There are several ways to integrate customized models. Plesae refer to Using a Custom Model with DeepStream — DeepStream 6.1.1 Release documentation