nvOCDR implementation in DeepStream

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) NVIDIA GeForce RTX 3090
• DeepStream Version 6.3
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only) 535.113.01
• Issue Type( questions, new requirements, bugs) 535.113.01
• 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)


I am trying to implement nvOCDR in DeepStream following these web page: Deploying nvOCDR to DeepStream - NVIDIA Docs
I have been able of generating the engines and building the nvOCDR library. However, I am facing some problems in the final step: Run the nvOCDR DeepStream Sample.
In this step the guide build the DeepStream pipeline using gst-launch, but I am interested on developing my own python app integrating the nvOCDR as PGIE or SGIE.
My question is the following. How is the configuration file for these models?
My idea is to use a config files like the other sample apps:

I hope I have explained myself correctly,
Thank you,


TAO’s documentation may be out of date, here is a latest example about nvOCDR, which is based on DS-6.4, you can refer to this, This sample has been fully tested

If you wish to use python, you can translate this c program into python

Perfect, thanks!

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