Deepstream 6.1 run secondary gie on outputs of all previous primary gies; operate-on-gie-id=all

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) - RTX 2070 dGPU
• DeepStream Version - 6.1
• JetPack Version (valid for Jetson only) - NA
• TensorRT Version - 8.4.2.1
• NVIDIA GPU Driver Version (valid for GPU only) - 510.
• Issue Type( questions, new requirements, bugs) - question on feature
• 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)

I am trying to create a Deepstream Pipeline that involves multiple detectors configured to run full-frame as primary. I also have a classifier running as secondary as third gie. I want this classifier to work on bboxes from all the previous detectors. Unfortunately, there is a setting called operate-on-gie-id=1 which seems to restrict this classifier to a single primary detector only.

[pgie1]
process-mode=1 #primary  detector
gie-unique-id=1
[pgie2]
process-mode=1 #another primary detector
gie-unique-id=2
[sgie1]
process-mode=2 #secondary clf
gie-unique-id=3
operate-on-gie-id=1 <--- select all previous pgies.

I want to know if its possible to run one classifier in secondary mode to bbox outputs of all previous primary detectors?

3

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

You can refer the link below to learn how to use multiple detectors.
https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps/tree/master/back-to-back-detectors