I’m using docker nvcr.io/nvidia/deepstream:6.0.1-devel, the image runs well but I can’t run any test successfully.
I try to update libgst*, but it is already newest.
And “root@e6ca3336189f:/# rm -r ~/.cache/gstreamer-1.0/registry.x86_64.bin” is no use ethier.
Please give me some advice, thx.
Did you install Nvidia-docker2 according to the guide ?
Please also share the command to start docker, and provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• 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)
• The pipeline being used
Thx for your reply.
No, I didn’t see the guide to install Nvidia-docker2, where is it?
GPU 1660
I just download the docker image nvcr.io/nvidia/deepstream:6.0.1-devel, and run the container by
xhost +
sudo docker run --gpus all -it -p 127.0.0.1:6666:6666 -p 6879:22 --shm-size=5g -v /tmp/.X11-unix:/tmp/.X11-unix -e GDK_SCALE -e GDK_DPI_SCALE -e DISPLAY=:1 nvcr.io/nvidia/deepstream:6.0.1-devel
And then what I did is just to build deepstream-test1-app and run ./deepstream-test1-app /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264, it occurred error “One element could not be creter. exit”.
Then I try to run this:
root@e6ca3336189f:/opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app# deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
** ERROR: <create_multi_source_bin:1424>: Failed to create element ‘src_bin_muxer’
** ERROR: <create_multi_source_bin:1517>: create_multi_source_bin failed
** ERROR: <create_pipeline:1326>: create_pipeline failed
** ERROR: main:688: Failed to create pipeline
Quitting
App run failed
I think the reason is the same, build is always ok but run failed.
I haven’t installed jetpack, shall I install it?
The referred environment is below:
root@e6ca3336189f:/opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app# deepstream-app --version-all
deepstream-app version 6.0.1
DeepStreamSDK 6.0.1
CUDA Driver Version: 11.4
CUDA Runtime Version: 0.0
TensorRT Version: 8.0
cuDNN Version: 8.2
Dewarper: not found
The installation guide is here: Installation Guide — NVIDIA Cloud Native Technologies documentation
what’s your GPU type? Can you check if command “nvidia-smi” can work in your docker environment?
You can also set the GST_DEBUG=3 to open more log info, like
GST_DEBUG=3 ./deepstream-test1-app /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264
Sorry， I think my former colleagues have installed nvidia-docker.
zyg@zyg-ubuntu:~/Desktop$ nvidia-docker --version
Docker version 20.10.5, build 55c4c88
DGPU 1660, “nvidia-smi” can work in my docker env.
In docker environment, the result of “nvidia-smi”
root@e6ca3336189f:/opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app# nvidia-smi
Sat Jan 7 05:28:44 2023
±----------------------------------------------------------------------------+
| NVIDIA-SMI 450.80.02 Driver Version: 450.80.02 CUDA Version: 11.4 |
|-------------------------------±---------------------±---------------------+
| 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 GeForce GTX 1660 Off | 00000000:01:00.0 On | N/A |
| 47% 24C P8 1W / 130W | 292MiB / 5943MiB | 11% Default |
| | | N/A |
±------------------------------±---------------------±---------------------+
±----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|
But in host, the CUDA version is lower than docker.
zyg@zyg-ubuntu:~/Desktop$ nvidia-smi
Sat Jan 7 13:23:53 2023
±----------------------------------------------------------------------------+
| NVIDIA-SMI 450.80.02 Driver Version: 450.80.02 CUDA Version: 11.0 |
|-------------------------------±---------------------±---------------------+
| 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 GeForce GTX 1660 Off | 00000000:01:00.0 On | N/A |
| 46% 24C P8 1W / 130W | 295MiB / 5943MiB | 11% Default |
| | | N/A |
±------------------------------±---------------------±---------------------+
±----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 973 G /usr/lib/xorg/Xorg 160MiB |
| 0 N/A N/A 1178 G /usr/bin/gnome-shell 132MiB |
±----------------------------------------------------------------------------+
I try it, the log is below:
root@e6ca3336189f:/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-test1# GST_DEBUG=3 ./deepstream-test1-app /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264
0:00:00.011588327 820 0x564e9dc23a10 WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory “nvstreammux”!
One element could not be created. Exiting.
The phenomenon is very similar to this topic, but no solution was found
FAIL to run deepstream 6-0 on T4 server - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums
Just from the log info, gstelementfactory.c:456:gst_element_factory_make: no such element factory “nvstreammux”!. There maybe something wrong with your env. So you may need to check it by yourself. You can refer to the link below to install the dependencies of the corresponding version.
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html?highlight=compatibility#platform-and-os-compatibility
Also we sugget you install the cuda version that needed in your host. The cuda in the Docker will depend on it on the host side.
Hello, I update the host driver to 525 and Cuda version to 11.8, now the test can run well.
And the command of running container has a problem: sudo docker run --gpus all -it -p 127.0.0.1:6666:6666 -p 6879:22 --shm-size=5g -v /tmp/.X11-unix:/tmp/.X11-unix -e GDK_SCALE -e GDK_DPI_SCALE -e DISPLAY=:1 [nvcr.io/nvidia/deepstream:6.0.1-devel]
, DISPLAY should be :0 or it will cause error.
Please tell me where I can find the standard command to run nvidia container. I didn’t see it in this site Docker Containers — DeepStream 6.1.1 Release documentation (nvidia.com).
By the way, I don’t install cuDNN and TRT in the host environment, does it have any effect on docker container?
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
You can refer the link below:
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html#dgpu
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.