Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
6.0.1
• TensorRT Version
8.0.1.6
• NVIDIA GPU Driver Version (valid for GPU only)
470.86
• Issue Type( questions, new requirements, bugs)
Question
• 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)
This may be as much a GStreamer question as a DeepStream question, but I’m wondering how people typically tackle what I’m assuming is a fairly common scenario:
Let’s say you have a tee that’s split the pipe towards their own respective sinks; however, let’s further assume that we want one branch to continue on as normal to its sink, and the other one (just after being split) to gate in a stateful way the flow of metadata to its own sink. Each sink is actually the same plugin, e.g. nvmsgconv.
The gating may let all, none, or parts of a batch through.
I obviously can’t just arbitrarily conduct operations on the metadata from one branch as the DeepStream metadata being passed through is all through pointers (i.e. one branch could affect the other). Is the best way to handle this to:
-
Copy the metadata/batch, perform operations on the copy (like removing or replacing), and output that data into the output of a gating plugin? (I’m leaning towards this, but I’m not exactly sure how to do this as of yet and will likely need to do a good bit more digging to do it.)
-
Insert additional metadata and create a customized version of nvmsgconv for the one sink?
-
A different way…?
Thanks in advance.