Deepstream-app multiple primary detectors

Setup:

deepstream-5.1 docker

I am trying to use multiple detctors within deepstream-app. My goal is to predict full frame with first detector and then predict on full frame with second detector. Then I want to process both detectors results in my plugin.
I’ve tried creating secondary-gie with process-mode=1, althought it seems to be detecting (does not draw on osd), but when I am postprocessing in my plugin obj_meta has detections only from first detector, second detector results are always missing.

I have also tried looking into back-to-back example, but so far I am not sure how to implement it in deepstream-app. Any guidance or tips would be really appreciated on what should I change to receive both detectors obj_meta

Please provide complete information as applicable to your setup.

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

This should be 0 for full frame