Problem when using tracker with re-identification

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) GPU
**• DeepStream Version 6.2
**• TensorRT Version
**• NVIDIA GPU Driver Version (valid for GPU only) 525.105.17
**• Issue Type( questions, new requirements, bugs) bug

I’m trying to connect tracking with re-identification to my application. In this case DeepSort. used as a base. Config config_tracker_NvDeepSORT.yml is unchanged. At startup, the following message appears and re-identification does not work.
If I connect DeepSort tracking through the deepstream-app application. The same.

resnet34_peoplenet_pruned_int8 used as PGIE

Starting pipeline

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is ON
[NvMultiObjectTracker] Loading TRT Engine for tracker ReID…
[NvMultiObjectTracker] Loading Complete!
ERROR: [TRT]: 3: [runtime.cpp::~Runtime::346] Error Code 3: API Usage Error (Parameter check failed at: runtime/rt/runtime.cpp::~Runtime::346, condition: mEngineCounter.use_count() == 1. Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior.

This “ERROR” will not impact the model engine build process, you can ignore it.

1 Like

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.