• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 7.0
• NVIDIA GPU Driver Version (valid for GPU only) 551.76
• Issue Type( questions, new requirements, bugs) Question
Is it possible to combine three classes (car, bus, truck) into class of vehicle using deepstream. Because sometimes YOLO changes detected object’s class and tracker assigns new id to it.
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• 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)
I don’t know why I need to put this, but OK.
what do you mean about “combine three classes (car, bus, truck) into class of vehicle using deepstream” and “YOLO changes detected object’s class”? deepstream is used to do inference with NVIDIA GPU acceleration. it will not modify the model’s classification.
No, I mean there are cases, when YOLO mistakenly classifies a car as a truck or a bus, and when it happens, tracker changes car’s id. And I don’t need to distinguish a car from a truck. I just wanted to know is it possible change pgie configuration so it will solve this problem.
I just edited my custom lib so it solved this problem. Thanks.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.