Segmentation fault while using a sgie in deepstream-app

[aniketrohara]

• Hardware: Jetson AGX Orin
• Deesptream7.0
• Jetpack 6.0 (6.0+b106 and 6.0+b87 both are installed) L4T 36.3.0
• TensorRT 8.6.2
• NVRM version: NVIDIA UNIX Open Kernel Module for aarch64 540.3.0
• Issue : i am trying to use a person attribute recognition model as sgie on a video after using a person detector as primary detector and i am using custom parser for using buffer of the secondary model but i am getting a segmentation fault and i am not able to understand its cause and how can i then resolve it.
• the secondary model that i am using is in pth form and i converted it to onnx using a separate python script.
• below drive contains all the files that i am using for my deepstream-app -c command and the secondary model as the primary one is YOLOv8s for person detection: PAR_forum - Google Drive
• Also currently the custom parser for secondary is just a print statement and yet i am getting the segmentation fault as you can see below:
  
  

[yuweiw]

You can try to use gdb tool to do a preliminary analysis of where the crash was.

$gdb  deepstream-app
$r -c <your_config_file>
after the crash
$bt

[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