Facing issue in passing multi-task classification model as a parent gie for the next classification model

[Pritam]

• Hardware Platform (Jetson / GPU) dGPU
• DeepStream Version 5.1
• TensorRT Version 7.2
• NVIDIA GPU Driver Version (valid for GPU only) 510
**• Issue Type( questions, new requirements, bugs)**questions

Hi,

I am using one detector and two classifier.
Detector1: Vehicle Detection (Label: Car)
Classifier1: MultiTask Classifier (Task1/Label1: SUV;SEDAN;HATCHBACK Task2/Label2:RED;ORANGE;BLACK )
Classifier2: MultiTask Classifier (Task1/Label1: X;Y;X Task2/Label2:A;B )
Now in Classifier2 I want to process only Sedan so what configuration should i set in the configuration.
(like operate-on-gie-id=0
operate-on-class-ids=???)

Please help.

[yuweiw]

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 set the operate-on-class-ids paras to the number in your label file.