Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.3
• JetPack Version (valid for Jetson only)
• TensorRT Version from the container
• NVIDIA GPU Driver Version (valid for GPU only) 535
• Issue Type( questions, new requirements, bugs) bug
• 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 see similar issue reported a few times but with no thorough follow up.
Myself and colleagues have recently spent a lot of time trying to debug the following error
GPUassert: invalid device ordinal src/modules/NvMultiObjectTracker/context.cpp 61
We observed it even though gpu-id was set to the same value in the config file where applicabble but also even if the gpu-id was the default 0 and the container had only one gpu available to it.
As of now it appears to us that this error usually appears when no sink is enabled in the deepstream app config file, but probably there are other situations that trigger it. We observed that with deepstream-app as well as with test5 app. Unfortunately, we are not able to debug the tracker any deeper.
Is this something that you are aware of and is it documented anywhere? Could the community know if there are other config cases that we should avoid?