How to add preprocess in secondary inference

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.1
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.2.5
• NVIDIA GPU Driver Version (valid for GPU only)

in deepstream document:
I saw :
“The Preprocess plugin (Gst-nvdspreprocess) for preprocessing on the pre-defined ROIs for primary inferencing.”
now , my project need to use pre-process plugin for secondary inference.
I want to implement 3D sequence before enter secondary model as deepstream-3d-action-recognition.
can you tell me how to do it?

Yes, nvdspreprocess is for PGIE currently. You can customized it as it is open source plugin.

can you get some suggestion to modify for secondary?

Please refer our document:

Gst-nvdspreprocess (Alpha) — DeepStream 6.1 Release documentation (

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.

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