Issue in running deepstream inside the docker container

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 6.0.1
• JetPack Version (valid for Jetson only) 4.6.3
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• 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)

I am facing an issue in running deepstream inside the docker container. I have pulled the 6.0.1 samples container using docker pull nvcr.io/nvidia/deepstream-l4t:6.0.1-samples.

I am using this command to execute the docker container. sudo docker run -it --rm --net=host --gpus all -e DISPLAY=$DISPLAY --device /dev/snd -v /tmp/.X11-unix/:/tmp/.X11-unix --runtime nvidia nvcr.io/nvidia/deepstream-l4t:6.0.1-samples
When I execute the deepstream-app --version command inside the docker container it throws “deepstream-app: error while loading shared libraries: libnvinfer.so.8: cannot open shared object file: No such file or directory”.

You can refer to this link to install the corresponding version of CUDA, TensorRT… on your host first.
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html?highlight=compatibility#id5

CUDA = 10.2
TensorRT = 8.2.1
Cudnn = 8.2.1.32
Jetpack = 4.6.1
These versions are installed on jetson. I have installed deepstream 6.0.1 version on jetson and it is working perfectly fine, but the docker container is throwing an error.

There may be some problems with TensorRT in the docker. You can try the following methods:
1.Reinstall the TensorRT in your docker
2.As you said:

You can mount the /usr/lib/aarch64-linux-gnu from your host.
3.Could you update the deepstream version to the latest(6.2)?

I have Jetson Tx2, and it doesn’t support Jetpack 5.2 and deepstream 6.2. Is there any other way to run the 6.0.1 deeepstream docker container on Tx2?

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

1.You can check if there is libnvinfer.so.8 in the /usr/lib/... path.
2.If you can find out which library is missing in Docker, you can modify the /etc/nvidia-container-runtime/host-files-for-container.d/l4t.csv file on your host to map it.

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