Enabling tracking in the NVIDIA Sample application causes invalid device ordinal ERROR

T4 GPU
deepstream:6.0-triton
TensorRT Version=8.0.1
NVIDIA GPU Driver Version 470.82.01 (Please note the recommended 470.63.01 is no longer available in the NVIDIA driver repository]

The NVIDIA Application with the default network of YoloV4 only runs if tracker is disabled … can anyone suggest why this error occurs if tracking is enabled? Any help appreciated, Thanks!


(deepstream-app:670): GLib-GObject-WARNING **: 22:47:54.960: value "TRUE" of typ                                      e 'gboolean' is invalid or out of range for property 'sync' of type 'gboolean'

(deepstream-app:670): GLib-GObject-WARNING **: 22:47:54.960: value "TRUE" of typ                                      e 'gboolean' is invalid or out of range for property 'qos' of type 'gboolean'
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-6.0/lib                                      /libnvds_nvmultiobjecttracker.so
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is ON
GPUassert: invalid device ordinal src/modules/NvMultiObjectTracker/context.cpp 6   ```

How to reproduce this error?

Hello Fiona,

Thank you for your reply. I’m using a T4 and was just wanting to confirm that setup works before trying further experiments. So have been following the instructions [Quickstart Guide — DeepStream 6.0 Release documentation (nvidia.com)](https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html#install-cuda-toolkit-11-4-1-cuda-11-4-update-1)
and also https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html#dgpu-setup-for-ubuntu

The only thing that I do after that is to set enable=0 in the deepstream_app_source1_detection_models.txt for the sink 0 to turn off sink 0 from being an EglSink.

Then I run the YoloV4 which is already selected in the sample config file with deepstream-app -c deepstream_app_source1_detection_models.txt

If I then disable the tracker with enable=0 I get performance timings like:


(deepstream-app:1016): GLib-GObject-WARNING **: 19:56:17.329: value "TRUE" of type 'gboolean' is invalid or out of range for property 'sync' of type '       gboolean'

(deepstream-app:1016): GLib-GObject-WARNING **: 19:56:17.329: value "TRUE" of type 'gboolean' is invalid or out of range for property 'qos' of type 'g       boolean'
0:00:08.831400639  1016 0x5612048f74c0 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info        from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepst       ream/deepstream-6.0/samples/models/tao_pretrained_models/yolov4/yolov4_resnet18.etlt_b1_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 5
0   INPUT  kFLOAT Input           3x544x960
1   OUTPUT kINT32 BatchedNMS      1
2   OUTPUT kFLOAT BatchedNMS_1    200x4
3   OUTPUT kFLOAT BatchedNMS_2    200
4   OUTPUT kFLOAT BatchedNMS_3    200

0:00:08.831485083  1016 0x5612048f74c0 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info        from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream       /deepstream-6.0/samples/models/tao_pretrained_models/yolov4/yolov4_resnet18.etlt_b1_gpu0_int8.engine
0:00:08.854524723  1016 0x5612048f74c0 INFO                 nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new mode       l:/opt/nvidia/deepstream/deepstream-6.0/samples/configs/tao_pretrained_models/config_infer_primary_yolov4.txt sucessfully

Runtime commands:
        h: Print this help
        q: Quit

        p: Pause
        r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
      To go back to the tiled display, right-click anywhere on the window.


**PERF:  FPS 0 (Avg)
**PERF:  0.00 (0.00)
** INFO: <bus_callback:194>: Pipeline ready

** INFO: <bus_callback:180>: Pipeline running

**PERF:  221.79 (221.56)
**PERF:  303.81 (268.76)
**PERF:  304.56 (281.55)
**PERF:  306.66 (288.30)
**PERF:  305.72 (292.00)
** INFO: <bus_callback:217>: Received EOS. Exiting ...

Quitting
App run successful