Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) 4090
• DeepStream Version 7.0
• 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)
When testing with the sample tritonclient/sample/configs/apps/vehicle_lpr_analytic from this repository, I encountered the following issues:
I have four video sources, which are processed in three branches:
- Branch 1: Sources
0, 1, 2 - Branch 2: Sources
1, 2, 3 - Branch 3: Sources
1, 2, 3
How can I configure config_metamux0.txt, msg-broker-comp-id, and msg-conv-comp-id so that each branch publishes messages to a separate Kafka topic?
I try to use one sink, it can use msg-conv-comp-id to filter but it only works for one topic, when I scale to 3 topics (3 sink type 6), it doesn’t work.
Expected Behavior:
- Topic 1 ↔ Branch 1 (Receives messages only from sources
0, 1, 2) (inference result with model in branch 1) - Topic 2 ↔ Branch 2 (Receives messages only from sources
1, 2, 3) - Topic 3 ↔ Branch 3 (Receives messages only from sources
1, 2, 3)
In other words, each topic should receive messages only from the sources within its corresponding branch when inferencing with that branch.