When i run deepstream sample, i'm getting following error message:-

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version DeepStreamSDK 6.1.0
• TensorRT Version (8.2.5-1+cuda11.4).

nm -D libnvinfer.so.4.1.0 | grep tensorrt_version
nm: ‘libnvinfer.so.4.1.0’: No such file

• NVIDIA GPU Driver Version (valid for GPU only) 470.129.06
• Issue Type( questions, new requirements, bugs)
(gst-plugin-scanner:41): GStreamer-WARNING **: 13:58:30.044: 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:41): GStreamer-WARNING **: 13:58:30.114: Failed to load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_udp.so’: librivermax.so.0: cannot open shared object file: No such file or directory
PuTTY X11 proxy: Unsupported authorisation protocol
PuTTY X11 proxy: Unsupported authorisation protocol
PuTTY X11 proxy: Unsupported authorisation protocol
PuTTY X11 proxy: Unsupported authorisation protocol
PuTTY X11 proxy: Unsupported authorisation protocol
0:00:00.897058313 40 0x55f19ea094d0 ERROR egladaption ext/eglgles/gstegladaptation_egl.c:160:gst_egl_adaptation_init_display:<sink_sub_bin_sink1> Could not init EGL display connection
0:00:00.897119421 40 0x55f19ea094d0 ERROR egladaption ext/eglgles/gstegladaptation_egl.c:183:gst_egl_adaptation_init_display:<sink_sub_bin_sink1> EGL call returned error 3000
0:00:00.897137719 40 0x55f19ea094d0 ERROR egladaption ext/eglgles/gstegladaptation_egl.c:185:gst_egl_adaptation_init_display:<sink_sub_bin_sink1> Couldn’t setup window/surface from handle
0:00:00.897146836 40 0x55f19ea094d0 ERROR nveglglessink ext/eglgles/gsteglglessink.c:536:egl_init:<sink_sub_bin_sink1> Couldn’t init EGL display
0:00:00.897174780 40 0x55f19ea094d0 ERROR nveglglessink ext/eglgles/gsteglglessink.c:562:egl_init:<sink_sub_bin_sink1> Failed to perform EGL init
** ERROR: main:716: Failed to set pipeline to PAUSED

nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Tue_Mar__8_18:18:20_PST_2022
Cuda compilation tools, release 11.6, V11.6.124
Build cuda_11.6.r11.6/compiler.31057947_0

2

Can you elaborate on how you installed DeepStream6.1 on your PC? Here is the guide for installing: Quickstart Guide — DeepStream 6.1 Release documentation (nvidia.com) Besides, what sample were you testing? please provide the command for the testing, thanks.

4

Please upgrade your driver to 510.47

5

I have installed deepstream as dgpu container. I have pulled the docker image and run the docker. Here is the sample run test ,before pulling the docker image, i have executed xhost + .

deepstream-app -c /opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt --gst-debug=1

After executing the above sample i’m getting the errors with the debug mode

6

When i installed nvidia driver above 510+.it was not working and when i checked the syslogs, i found the below error messages and i downgraded the driver version to 470 and it fixed the issue.

NVRM: supported through the NVIDIA 470.xx Legacy drivers. Please
NVRM: visit Unix Drivers | NVIDIA for more
NVRM: information. The 515.48.07 NVIDIA driver will ignore
this GPU. Continuing probe…

7

Which GPU you are using?

8

We need GPU driver 510.47+ for deepstream 6.1

9

| NVIDIA-SMI 470.129.06 Driver Version: 470.129.06 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 Tesla K80 On | 00000000:00:1E.0 Off | 0 |
| N/A 32C P8 30W / 149W | 4MiB / 11441MiB | 0% Default |
| | | N/A |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 813 G /usr/lib/xorg/Xorg 3MiB |

10

The following packages have unmet dependencies:
nvidia-driver-510 : Depends: libnvidia-gl-510 (= 510.73.08-0ubuntu1) but it is not going to be installed
Depends: nvidia-dkms-510 (= 510.73.08-0ubuntu1)
Depends: nvidia-kernel-source-510 (= 510.73.08-0ubuntu1) but it is not going to be installed
Depends: libnvidia-extra-510 (= 510.73.08-0ubuntu1) but it is not going to be installed
Depends: libnvidia-encode-510 (= 510.73.08-0ubuntu1) but it is not going to be installed
Depends: nvidia-utils-510 (= 510.73.08-0ubuntu1) but it is not going to be installed
Depends: libnvidia-fbc1-510 (= 510.73.08-0ubuntu1) but it is not going to be installed
Recommends: libnvidia-compute-510:i386 (= 510.73.08-0ubuntu1)
Recommends: libnvidia-decode-510:i386 (= 510.73.08-0ubuntu1)
Recommends: libnvidia-encode-510:i386 (= 510.73.08-0ubuntu1)
Recommends: libnvidia-fbc1-510:i386 (= 510.73.08-0ubuntu1)
Recommends: libnvidia-gl-510:i386 (= 510.73.08-0ubuntu1)
E: Unable to correct problems, you have held broken packages.

11

Did you remove 470 driver?
Try sudo apt-get install cuda-drivers

14

Sorry for the late reply . I have tried installing from the 510 driver by download the package manually and then installed it . But it was throwing the error which I mentioned above . So I removed it and installed 470 from the apt-get package awhile try to install 510 I removed 470 .

15

Can you try to re-install DeepStream 6.1 with steps described in Quickstart Guide — DeepStream 6.1.1 Release documentation ?

17

Trying to install Deepstream as a docker .

18

Seems currently GPU driver version is 470.129.06 for K80, if you use this card, you can consider use deepstream 6.0, but we strongly suggest you use latest deepstream version.
did you have another nvidia GPU cards?

19

No we don’t .

20

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

Either use DS 6.0, or you can consider buy one supported GPU if you choose DS.
https://docs.nvidia.com/metropolis/deepstream/6.0/dev-guide/text/DS_Quickstart.html#dgpu-setup-for-ubuntu

22

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