Test app does not work in deepstream docker

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hello.
I am running a deepstream docker with

sudo docker run --gpus all -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -w /root nvcr.io/nvidia/deepstream:4.0.2-19.12-samples

That works and

nvidia-smi

produces proper output.
However if I try to run any test app with the command :

root@34bfa34d51ea:~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app# deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt 
exit
** ERROR: <main:651>: Failed to set pipeline to PAUSED
Quitting
App run failed

Any ideas what’s wrong with it?

Regards, Sergei.

2

What’s your gpu and driver version ?

3

GPU is Quadro M100M and the latest driver version:

$ nvidia-smi
Fri Feb  7 12:55:27 2020       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 440.44       Driver Version: 440.44       CUDA Version: 10.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  Quadro M1000M       Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   36C    P8    N/A /  N/A |    441MiB /  4041MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0       557      G   /usr/lib/Xorg                                 31MiB |
|    0       768      G   /usr/lib/Xorg                                110MiB |
|    0       814      G   /usr/bin/gnome-shell                         202MiB |
|    0      1073      G   /usr/bin/nextcloud                             0MiB |
|    0      1337      G   /usr/lib/firefox/firefox                      19MiB |
+-----------------------------------------------------------------------------+
4

For Tesla for HPC and supercomputing applications, go to www.nvidia.com/object/tesla_wtb.html
For GeForce for entertainment, go to GeForce RTX 20 Series Graphics Cards and Laptops
For Quadro for professional visualization, go to www.nvidia.com/object/workstation_wheretobuy.html

Deepstream sdk is for hpc and computing. it can run on NVIDIA dGPU card products such as NVIDIA® Tesla® T4 and P4, NVIDIA® GeForce® GTX 1080, and NVIDIA® GeForce® RTX 2080

5

Thank you.
Does DeepStream work on RTX 2080Ti?
Is there a complete list of GPUs that support DeepStrem?
What is hpc term in the response above “Deepstream sdk is for hpc and computing.”

Regards, Sergei.

6

2080Ti is OK.
HPC is High-performance computing