Issue in running deepstream-app

Please provide complete information as applicable to your setup.

  • 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 had the above configs on my board previously with ubuntu 22.04 then i performed a partial update on ubuntu after which somehow deepstream sdk 7.0 got removed and my tensorrt version got degraded to 6.0

  • So i reinstalled the deepstream sdk from the tbz2 file and it got installed properly.
  • Then i tested my custom prebuilt app and it worked properly
  • Then i tried to make a custom parser for my another app but it gave me following error: /opt/nvidia/deepstream/deepstream/sources/includes/nvdsinfer_custom_impl.h:127:10: fatal error: NvCaffeParser.h: No such file or directory
    127 | # include “NvCaffeParser.h”.
  • So i upgraded the tensorrt back to 8.6.2 by downloading and installing files specified in Installation — DeepStream documentation 6.4 documentation and i downloaded them from Index of /compute/cuda/repos/ubuntu2204/sbsa
  • Now after installation the make command got executed properly but the app gets stuck at the following point: and i have to interrupt it to stop it.

It looks like jetpack’s software stack is broken, You can try the following commands.

sudo apt update
sudo apt install nvidia-jetpack

For more information, refer this link
https://docs.nvidia.com/jetson/jetpack/install-setup/index.html#install-jetpack-components-on-jetson-linux

If still not work normally, try to reburn the jetpack with the Nvidia SDKManager.

but is it okay if i do it, as i have some important data on my board and i have not backed it up so, won’t it delete anything, just like the ubuntu update did?

If you do not use sdkmanger to re-burn the system, the data will not be deleted. It is recommended that you make a backup for reburn.

i used the sudo apt update and it gave me few warnings:
W: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm64/InRelease: Key is stored in legacy trusted.gpg keyring (/etc/apt/trusted.gpg), see the DEPRECATION section in apt-key(8) for details.

W: https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/arm64/InRelease: Key is stored in legacy trusted.gpg keyring (/etc/apt/trusted.gpg), see the DEPRECATION section in apt-key(8) for details.

W: https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/arm64/InRelease: Key is stored in legacy trusted.gpg keyring (/etc/apt/trusted.gpg), see the DEPRECATION section in apt-key(8) for details.

W: https://nvidia.github.io/nvidia-docker/ubuntu18.04/arm64/InRelease: Key is stored in legacy trusted.gpg keyring (/etc/apt/trusted.gpg), see the DEPRECATION section in apt-key(8) for details.

then after using sudo apt install nvidia-jetpack it is giving following error:
E: Unable to locate package nvidia-jetpack

These warnings seem to be caused by incorrect jetpack installation. Please refer to the link I provided above. You can try the guidelines inside.

reburning jetpack worked for me thanks for the help

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