As stated I want to ensure I have a functional Docker setup for running DeepStream 5.1 containers. Issues documented bellow:
• Hardware Platform (Jetson / GPU)
NVIDIA RTX A2000 Laptop GPU
• DeepStream Version
DeepStream5.1
• NVIDIA GPU Driver Version (valid for GPU only)
516.94
• Issue Type( questions, new requirements, bugs)
I am working to get the docker sample running.
• 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)
I have WSL 2 installed on Windows 10 Pro Version 21H2
Then I installed Ubuntu 22.04 LTS:
Docker Desktop installed with the result in Ubuntu:
docker --version
Docker version 20.10.17, build 100c701
After that on windows I installed the latest Nvidia driver found here:
I followed this procedure: Installation Guide — NVIDIA Cloud Native Technologies documentation to get the Nvidia toolkit setup, but did not install the Linux driver due to using WSL2.
Once completed used the command:
sudo docker run --rm --gpus all nvidia/cuda:11.0.3-base-ubuntu20.04 nvidia-smi
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 515.65.01 Driver Version: 516.94 CUDA Version: 11.7 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA RTX A200... On | 00000000:01:00.0 Off | N/A |
| N/A 37C P0 13W / N/A | 0MiB / 4096MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| No running processes found |
+-----------------------------------------------------------------------------+
however when I run:
sudo docker run --gpus all -it --rm --net=host --privileged -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-5.1 nvcr.io/nvidia/deepstream:5.1-21.02-samples
then in the docker run:
deepstream-app -c configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt
this yields the following error:
(gst-plugin-scanner:12): GStreamer-WARNING **: 15:45:48.107: Failed to load plugin '/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_inferserver.so': libtritonserver.so: cannot open shared object file: No such file or directory
(gst-plugin-scanner:12): GStreamer-WARNING **: 15:45:48.115: Failed to load plugin '/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_infer.so': /usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_infer.so: undefined symbol: cuGraphicsEGLRegisterImage
** ERROR: <parse_config_file:532>: parse_config_file failed
** ERROR: <main:627>: Failed to parse config file 'configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt'
Quitting
App run failed
I am new to running DeepStream in general and have inherited a Docker based project using DeepStream5.1, so any help would be appreciated. The actual project is running on a Lenovo ThinkEdge SE70, but I was hoping to be able to do R&D development on my personal machine. If there is a recommendation for the cleanest workflow here I am willing to make a change.
Currently running samples found here:
https://docs.nvidia.com/metropolis/deepstream/5.1/dev-guide/text/DS_docker_containers.html