Couldn't run deepstream sample app using nvinferserver inside a docker container

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU): Tesla T4
• DeepStream Version: 6.4
• JetPack Version (valid for Jetson only)
• TensorRT Version: 8.6.1.6-1+cuda12.0
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs): bug

• 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)
Hi, this is what I did to run a sample DeepStream app which is using Gst - nvinferserver. To run inside a docker container.

  1. I followed the instruction provided in the readme file of this repo deepstream_python_apps/apps/deepstream-rtsp-in-rtsp-out at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub
  2. I mounted a folder where the python and config files are added from the given github repo relevant to the app and some necessary files which are in the common folder deepstream_python_apps/apps/common at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub, which are used to run the app.
  3. inside the container I installed all the requirements using the commands given in readme file:

And I then try to run this command

python3 deepstream_test1_rtsp_in_rtsp_out.py -h

But I got this error

> root@ip-192-168-2-157:/opt/nvidia/deepstream/deepstream-6.4/fast-api/NVIDIA-AI-IOT deepstream_python_apps master apps-deepstream-rtsp-in-rtsp-
> out# python3 deepstream_test1_rtsp_in_rtsp_out.py -h
> Traceback (most recent call last):
>   File "/opt/nvidia/deepstream/deepstream-6.4/fast-api/NVIDIA-AI-IOT deepstream_python_apps master apps-deepstream-rtsp-in-rtsp-out/deepstream_test1_rtsp_in_rtsp_out.py", line 23, in <module>
>     import pyds
> ImportError: libpython3.8.so.1.0: cannot open shared object file: No such file or directory

I checked the pyds version

root@ip-192-168-2-157:/opt/nvidia/deepstream/deepstream-6.4/fast-api/NVIDIA-AI-IOT deepstream_python_apps master apps-deepstream-rtsp-in-rtsp-
out# pip show pyds
Name: pyds
Version: 1.1.8
Summary: Install precompiled DeepStream Python bindings extension
Home-page: nvidia.com
Author: NVIDIA
Author-email: 
License: 
Location: /usr/local/lib/python3.10/dist-packages
Requires: pgi, PyGObject
Required-by:

So I upgraded using this command
`

> pip install --upgrade --force-reinstall pyds

Now the pyds version is this

root@ip-192-168-2-157:/opt/nvidia/deepstream/deepstream-6.4/fast-api/NVIDIA-AI-IOT deepstream_python_apps master apps-deepstream-rtsp-in-rtsp-
out# pip show pyds
Name: pyds
Version: 0.2.0
Summary: A Python module to read, write and manipulate PDS labels.
Home-page: https://github.com/jashandeep-sohi/pyds
Author: Jashandeep Sohi
Author-email: jashandeep.s.sohi@gmail.com
License: GPLv3
Location: /usr/local/lib/python3.10/dist-packages
Requires: 
Required-by:

Then I again ran the command it gave some output regarding the usage of the app

so I tried to run the server by the commands given in the readme file for nvinferserver

  1. run a .sh file to prepare the triton model repo

/opt/nvidia/deepstream/deepstream-6.4/samples/prepare_ds_triton_model_repo.sh

  1. run the app by modifying the following command with an rtsp url

python3 deepstream_test1_rtsp_in_rtsp_out.py -i rtsp://sample_1.mp4 rtsp://sample_2.mp4 rtsp://sample_N.mp4 -g nvinferserver

The app started running And now I am getting this error related to pyds

So I need to know why this bug is something internal or not and which pyds version do I have to exactly use to avoid this error.

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 better to build and install pyds according to deepstream_python_apps/bindings at master · NVIDIA-AI-IOT/deepstream_python_apps (github.com)

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