Run SGIE Classifier on every nth tracked object

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)


Is it possible to only do SGIE inference on every nth frame of a given object?

ie. if I have tracked an object A through frames 100-200 in a video, I want to only do SGIE classification on that object A on frames 100, 102, 104 etc. etc…
Another object B is tracked from frames 150-250 and should only be classified on frames 150, 152, 154…

It seems that “interval=1” is only valid for PGIE?



  1. there is no this kind of setting, if interval = 0, all objects will do sgie inference.
  2. yes, it is only for PGIE, please refer to Gst-nvinfer — DeepStream 6.1.1 Release documentation.

Would it be possible to allow for secondary-reinfer-interval property to work on any network type? Currently it seems to only be supported on classifiers?



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.

it supports Detector & Classifier, please find secondary-reinfer-interval in this Gst-nvinfer — DeepStream 6.1.1 Release documentation

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