Why is bInferDone not 1 during semantic segmentation?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.2
• 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)

hello. In deepstream 6.2, it was configured with the following pipeline: source -> pgie -> segvisual -> osd -> window-sink.

  1. When I print FrameMeta’s binferdone on the pgie src pad, it comes out as 0. I think it should come out value 1. Does binferdone not be processed separately internally during segmentation? (is it works on detection)
  2. And when pgie interval>0, can it be said that user_meta->seg_meta is preserved?

Thank you

3
  1. what do you use FrameMeta’s binferdone to do? nvinfer plugin is opensource. only in attach_metadata_detector it is be set to 1.
  2. no, you can set interval=10 to check.
4
  1. what do you use FrameMeta’s binferdone to do?
    When binferdone is 0, I tried to use the previous Mask, but the flag cannot be used. It seems to only have to do with detection.
  2. Yes, confirmed
5

nvinfer plugin is opensource. you can set binferdone to 1 in attach_metadata_segmentation, then rebuild and replace /opt/nvidia/deepstream/deepstream/lib/gst-plugins/libnvdsgst_infer.so with the new so.