Segmentation fault while running deepstream python app

[erjunsheng]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
Jetson Orin NX
• DeepStream Version
DeepStream 7.0
• JetPack Version (valid for Jetson only)
JetPack 6.0
• TensorRT Version
TensorRT 8.6.2.3
• NVIDIA GPU Driver Version (valid for GPU only)
NVIDIA UNIX Open Kernel Module for aarch64 540.3.0
• Issue Type( questions, new requirements, bugs)
I met an error when running deepstream app

dla engine built successfully but the app turned out segmentation fault

[junshengy]

First confirm that DLA is working properly.

If you modify the configuration file dstest1_pgie_config.txt of deepstream-test1 like below.

model-engine-file=../../../../samples/models/Primary_Detector/resnet18_trafficcamnet.etlt_b1_dla0_int8.engine

enable-dla=1
use-dla-core=0

Then run sudo tegrastats |grep NVDLA0, Is there any change in the status of NVDLA0?

[erjunsheng]

I met another error when running the app. Is it because I’m using display?

[junshengy]

@erjunsheng

Is it because I’m using display?

Do you run the python application in ssh ? Try the following command line.

export `cat /proc/$(pidof "gnome-shell")/environ | tr '\0' '\n' | grep ^DISPLAY=`

[erjunsheng]

Yes I’m running it with ssh. How should I adjust the code or command to run it?

I tried to run it directly on orin. And the error above showed.

[junshengy]

Make sure you clone the deepstream_python_apps repo under <DeepStream ROOT>/sources/deepstream_python_apps

NVIDIA-AI-IOT/deepstream_python_apps/blob/master/bindings/README.md#13-initialization-of-submodules

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks