Some problems about deepstream_test2

Hardware Platform : GPU
DeepStream Version : 5.1
Issue Type(questions : new requirements
Requirement details :
I am using deepstream-test2 to implement something like this:

  1. YOLOv5 model plus secondary model U-Net segmentation model;
  2. segment the target in the pgie and render the segmentation result to the original video frame.
    I would like to ask if it is possible to implement that functionality.

Here is a topic from another customer, objection detection + segmentation was implemented in this example which is also based on deepstream-test2, you may use it as a reference.
How to use object detection and segmentation models in the same pipeline and get the outputs in the screen - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums

Sorry, I don’t see another customer’s thread and can’t do a click through. Did you forget to put the link for me.

My bad, update with the link.

Ok! Thank you very much @yingliu

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