Deepstream-App not working on Jetson Orin Nanod

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, , ,
1

So I followed the following tutorial to run a YoloV11 model with TensorRT and Deepstream on a Jetson Orin Nano:

However, when I start the Deepstream-App, a window opens for 1sec and closes right after. Here is the output in the terminal:

% deepstream-app -c deepstream_app_config.txt
0:00:07.036971198 42484 0xaaab0476b520 INFO                 nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2092> [UID = 1]: deserialized trt engine from :/home/petri/Test/YoloAPP/DeepStream-Yolo/model_b1_gpu0_fp16.engine
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: [Implicit Engine Info]: layers num: 2
0   INPUT  kFLOAT input           3x640x640       
1   OUTPUT kFLOAT output          8400x6          

0:00:07.490956357 42484 0xaaab0476b520 INFO                 nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2195> [UID = 1]: Use deserialized engine model: /home/petri/Test/YoloAPP/DeepStream-Yolo/model_b1_gpu0_fp16.engine
0:00:07.498714001 42484 0xaaab0476b520 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/home/petri/Test/YoloAPP/DeepStream-Yolo/config_infer_primary_yolo11.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:301>: Pipeline ready


(deepstream-app:42484): GLib-GObject-WARNING **: 14:47:15.969: g_object_set_is_valid_property: object class 'GstNvJpegDec' has no property named 'DeepStream'
NvMMLiteOpen : Block : BlockType = 277 
NvMMLiteBlockCreate : Block : BlockType = 277 
** INFO: <bus_callback:287>: Pipeline running

nvstreammux: Successfully handled EOS for source_id=0
zsh: segmentation fault (core dumped)  deepstream-app -c deepstream_app_config.txt

I am using a Jetson Orin Nano with
Jetpack 6.0,
CUDA 12.2,
Deepstream SDK 6.4,
GStreamer Core Library 1.20.3,

I really don’t know what to do and I am looking forward to your help and thank you in advance.

4

Is this still a support issue? I tested the program on Jetpack 6.1 and DeepStream 7.1 and it works fine, can you try reflashing JP-6.1 and DS-7.1?

# install  ultralytics
git clone https://github.com/ultralytics/ultralytics.git
cd ultralytics
python3 -m build
cd dist
pip install ./ultralytics-8.3.104-py3-none-any.whl
pip install numpy==1.26.4

# export onnx
cd /path/to/DeepStream-Yolo/utils
wget https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s.pt
python3 export_yolo11.py -w yolo11s.pt --dynamic

# modify deepstream app configuration 
deepstream-app -c deepstream_app_config.txt

For more questions, please consult the author on GitHub