NGC Container on Jetson Orin Nano

Project help
, , ,
1

Hi,

We have deployed the container on jetson Orin nano (reComputer Seed studio J3010-Edge) running latest balena OS. we have used the base image from NGC

nvcr.io/nvidia/deepstream:7.1-triton-multiarch

  1. L4T version - 36.4.3 and firmware is also up to date.
  2. Jetpack OS - 6.2
  3. cuda-python etc.

All the dependencies has been resolved and on place.

To be Specific, Under the NGC base image, we have installed the following.

a. Added repos to the nvidia list.
b. Installed tegra
c. Installed Xserver
d. Since the base image is having the deepstream additionally we are doing
/opt/nvidia/deepstream/deepstream-7.1/user_additional_install.sh

we are having the onnx model with the repo has been setup for the same.

we tried to ran this deepstream_test_3.py python example with right config file, nvinferserver and followed by --no-display [ To ensure fakesink has to be used.]

Am getting the following result.

root@bef44492d759:/opt/nvidia/deepstream/deepstream-7.1# python3 my_deepstream_app.py -i file:///opt/nvidia/deepstream/deepstream-7.1/HSR1_1Min20250107_1001
25.mp4 -c config_triton.txt -g nvinferserver --no-display
<frozen importlib._bootstrap_external>:1184: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
<frozen importlib._bootstrap_external>:1184: FutureWarning: The cuda.cuda module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.driver module instead.
nvbufsurftransform: Could not get EGL display connection
{'input': ['file:///opt/nvidia/deepstream/deepstream-7.1/HSR1_1Min20250107_100125.mp4'], 'configfile': 'config_triton.txt', 'pgie': 'nvinferserver', 'no_display': True, 'file_loop': False, 'disable_probe': False, 'silent': False}
Creating Pipeline
 
Creating streamux
 
Creating source_bin  0
 
Creating source bin
source-bin-00
Creating Pgie
 
Creating tiler
 
Creating nvvidconv
 
Creating nvosd
 
Creating Fakesink
 
WARNING: Overriding infer-config batch-size 0  with number of sources  1
 
Is it Integrated GPU? : 1
Adding elements to Pipeline
 
Linking elements in the Pipeline
 
Now playing...
0 :  file:///opt/nvidia/deepstream/deepstream-7.1/HSR1_1Min20250107_100125.mp4
Starting pipeline
 
0:00:00.149830188   499 0xaaaadb9fde90 WARN           nvinferserver gstnvinferserver_impl.cpp:365:validatePluginConfig:<primary-inference> warning: Configuration file batch-size reset to: 1
INFO: TrtISBackend id:1 initialized model: dummy_model
nvbufsurface: Could not get EGL display connection
nvbufsurface: Can't get EGL display
ERROR: Error: Could not map EglImage from NvBufSurface for nvinfer
ERROR: Failed to add surface buffer into pool
ERROR: Failed to creat nvbufsurface
Decodebin child added: source
 
Decodebin child added: decodebin0
 
Warning: gst-library-error-quark: Configuration file batch-size reset to: 1 (5): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinferserver/gstnvinferserver_impl.cpp(365): validatePluginConfig (): /GstPipeline:pipeline0/GstNvInferServer:primary-inference
Decodebin child added: qtdemux0
 
Decodebin child added: multiqueue0
 
Decodebin child added: h264parse0
 
Decodebin child added: capsfilter0
 
Decodebin child added: nvv4l2decoder0
 
Opening in BLOCKING MODE
NvMMLiteOpen : Block : BlockType = 261
NvMMLiteBlockCreate : Block : BlockType = 261
In cb_newpad
 
gstname= video/x-raw
features= <Gst.CapsFeatures object at 0xffff7d5f80a0 (GstCapsFeatures at 0xaaaadbbaa470)>
Segmentation fault

Can anybody help us on this?

Kind note that we had connected to display through HDMI Interface.
also setup the environmental variable as DISPLAY=:0