I installed deepstream 6.3 environment, when I run the program, why does it load the dependencies of deepstream 6.1?

[jrrg5533]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
6.3
• JetPack Version (valid for Jetson only)
• TensorRT Version
8.4
• NVIDIA GPU Driver Version (valid for GPU only)
535.54.03
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

The original environment of my machine was deepsteam6.1.1, and then I uninstalled it by running sudo ./uninstall.sh according to the official tutorial, and deleted cuda and tensorRT, etc., and then reinstalled the deepstream6.3 environment according to the documentation, but why did I run the program it will still load deepstream6.1? Why is my tensorRT version 8.4? Logically speaking, it is 8.5

[jrrg5533]

root@box:/home# deepstream-app --version-all
deepstream-app version 6.3.0
DeepStreamSDK 6.3.0
CUDA Driver Version: 12.2
CUDA Runtime Version: 12.1
TensorRT Version: 8.4
cuDNN Version: 8.4
libNVWarp360 Version: 2.0.1d3

[jrrg5533]

root@box:/home# python3 support_multi_rtsp.py
Traceback (most recent call last):
File “support_multi_rtsp.py”, line 5, in
import pyds
ImportError: /opt/nvidia/deepstream/deepstream-6.1/lib/libnvds_meta.so: cannot open shared object file: No such file or directory

[jrrg5533]

My original environment is deepstream6.1.1,the steps to uninstall the environment are as follows:

1.Uninstall deepstream(https://docs.nvidia.com/metropolis/deepstream/6.1.1/dev-guide/text/DS_Quickstart.html#dgpu-setup-for-ubuntu)

2.Uninstall cuda:
sudo apt-get --purge remove "*cuda*" "*cublas*" "*cufft*" "*cufile*" "*curand*" \
 "*cusolver*" "*cusparse*" "*gds-tools*" "*npp*" "*nvjpeg*" "nsight*" "*nvvm*"

3.Uninstall driver:
./NVIDIA-Linux-x86_64-xxx.run --uninstall 

or

a.sudo apt-get --purge remove "*nvidia*" "libxnvctrl*"

b.sudo apt-get autoremove

c.find / -name "*nvidia*",Manually delete the driver that does not match the query result using rm -rf


4.Uninstall tensorRT:
sudo apt-get --purge remove libnvinfer8=8.4.1-1+cuda11.6 libnvinfer-plugin8=8.4.1-1+cuda11.6 libnvparsers8=8.4.1-1+cuda11.6 \
  libnvonnxparsers8=8.4.1-1+cuda11.6 libnvinfer-bin=8.4.1-1+cuda11.6 libnvinfer-dev=8.4.1-1+cuda11.6 \
  libnvinfer-plugin-dev=8.4.1-1+cuda11.6 libnvparsers-dev=8.4.1-1+cuda11.6 libnvonnxparsers-dev=8.4.1-1+cuda11.6 \
  libnvinfer-samples=8.4.1-1+cuda11.6 libcudnn8=8.4.1.50-1+cuda11.6 libcudnn8-dev=8.4.1.50-1+cuda11.6 \
  python3-libnvinfer=8.4.1-1+cuda11.6 python3-libnvinfer-dev=8.4.1-1+cuda11.6

[junshengy]

1. If you run native deepstream-app, can it work normally ?

2. try which deepstream-app to find path of deepstream-app then run ldd deepstream. what the output ?

3.try install.sh in /opt/nvidia/deepstream/deepstream

4. user_deepstream_python_apps_install.sh reinstall python bindings.

5. It is recommended to use docker, which is a simple and convenient method

[jrrg5533]

Hi, I met you again, my old friend. You are really amazing. Thank you for your suggestion. I have redone Python binding to solve the problem. By the way, do you know why my TensorRT version is not 8.5?

[junshengy]

@jrrg5533

TensorRT Version

ls -l /usr/lib/x86_64-linux-gnu/libnvinfer.so

Does this library exist? Is its soft link to version 8.4?
Maybe you can try docker

[jrrg5533]

Yes, it exists. Docker is excellent, but this is a development environment

/usr/lib/x86_64-linux-gnu/libnvinfer.so → libnvinfer.so.8.5.3

[junshengy]

If you execuse install.sh in /opt/nvidia/deepstream/deepstream to flush cache

Or reboot ?

Are there any changes?

I’m not quite sure why this is the case

[jrrg5533]

I’m sorry, it still doesn’t work.Anyway, thank you for your help