Nvdspreprocess for detected objects

Accelerated Computing Intelligent Video Analytics DeepStream SDK
#1

Please provide complete information as applicable to your setup.

• Hardware Platform (GPU)
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only)
• TensorRT Version: 8.0
• 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)

Hello Nvidia, I have a question. Does nvdspreprocess plugin support preparing multiple tensors based on detected objects metadata generated on the fly (Or implementating through “custom-tensor-preparation-function” interface is possible). I want to apply some transform (perspective transform) and feed the prepared multiple tensors to the downstream nvinfer component based on metadata generated by upstream nvinfer components.
Thanks and sorry for bad English :D

#3

Seems you need pgie and sgie nvinfer plugin. nvinfer plugin is open source. You can do any process.

#4

Hi, what I’m asking is if implementing nvdspreprocess with variable number of tensors through “custom-tensor-preparation-function” interface without modifying plugin source code is possible. Thanks

#5

any advice?

#6

Seems yes.

#8

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