Different detection thresholds per input stream

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only)
• TensorRT Version not relevant
• NVIDIA GPU Driver Version (valid for GPU only) not relevant
• Issue Type( questions, new requirements, bugs) questions
• 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)

We are trying to reduce spurious detections in our yolo model by setting different thresholds and min/max values for our classes in inference config file like advised here:
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_ref_app_deepstream.html#reducing-spurious-detections

We’d like to be able to define different values for different streams, but it doesn’t seem to be documented anywhere. Is this possible, if so - how? Is there a suggested workaround? All those streams use the same model weights so for performance reasons we’d prefer to avoid starting multiple instances of the application.

Kind regards,
D

This is not supported now.

These are attributes of nvinfer plugin - Gst-nvinfer — DeepStream 6.0 Release documentation, we provide the nvinfer plugin source code (/opt/nvidia/deepstream/deepstream-6.0/sources/libs/nvdsinfer/), you could custom it by yourself.

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