Error using deepstream to run yolo model

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

JETSON AGX ORIN
JETPACk - 5.1-b147 L4T 35.2.1
64 RAM
Ubuntu 20.04 (5.10.104-tegra)
CUDA - 11.4.315
cuDNN - 8.6.0.166
TensorRT - 8.5.2.2
PyTorch - 2.0.0
Torchvision - 0.15.1
Deepstream 6.2

QUESTIONS
i’m trying to run my YOLO model on deepstream but it return this error :
sponskar@sponskar-AI:~/DeepStream-Yolo$ deepstream-app -c deepstream_app_config.txt
** ERROR: main:716: Failed to set pipeline to PAUSED
Quitting
nvstreammux: Successfully handled EOS for source_id=0
ERROR from sink_sub_bin_sink1: GStreamer error: state change failed and some element failed to post a proper error message with the reason for the failure.
Debug info: gstbasesink.c(5367): gst_base_sink_change_state (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstNv3dSink:sink_sub_bin_sink1:
Failed to start
App run failed

3

Have you modified the code or configuration files?

If you want to run yolo through deepstream, you can refer to this project and modify it according to your model

4

Yes, I’m currently working through this tutorial, which incorporates the DeepStream-Yolo project :

seeedstudio - YOLO on jetson

I adjusted the DeepStream configuration to align with my model as instructed in the tutorial. However, upon running ‘deepstream-app -c deepstream_app_config.txt,’ it’s throwing errors. Could this be due to running it via SSH?

5

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

It is possible. try to export DISPLAY=:x, x represents the value from cat /proc/$(pidof "gnome-terminal-server")/environ | tr '\0' '\n' | grep ^DISPLAY=

6

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