Deepstream on Nano: running detectnet and classification at same time

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Hello:
i am running a custom detectnet model/engine on JetsonNano and I would need to add a classification model/engine at the same time.
would this be possible to have 2 (or more) separate models/engines configured to be selected by deepstream at the same time? if yes, could you share some sample configs or links/infos where I can get some further details?

thanks so much!

Deepstream: create custom age gender model with TLT
2

Reference:

/opt/nvidia/deepstream/deepstream/samples/configs/tlt_pretrained_models/deepstream_app_source1_dashcamnet_vehiclemakenet_vehicletypenet.txt

3

This works for detectnet & Co models, but not for a classification model… at least I was not able to get it running.
→ see my other post here

4

Can you run /opt/nvidia/deepstream/deepstream/samples/configs/tlt_pretrained_models/deepstream_app_source1_dashcamnet_vehiclemakenet_vehicletypenet.txt successfully?
More, the secondary-gie0 or secondary-gie1 is a classification model.

BTW, what do you mean “detectnet & Co” ?