Deepstream-app: error while loading shared libraries: libnvinfer.so.6: cannot open shared object file + ubuntu 18.04

Accelerated Computing Intelligent Video Analytics DeepStream SDK
22

please install cuda 10.1 and try again.

23

Ok. I am using this CUDA 10.2 with OpenCV and CuDNN combination for development. I can’t remove CUDA 10.02, but I think I can install another CUDA version 10.1 and use it in virtual environment for DeepStream Python setup.

25

@Amycao, I have downloaded the docker image DeepStream | NVIDIA NGC and tried to run the C samples. Now this docker image have all required Cuda and TensorRT versions for Deepstream 4.0.2. Still the C samples are not working.

$ deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/config_infer_primary.txt

** ERROR: <create_multi_source_bin:714>: Failed to create element 'src_bin_muxer'
** ERROR: <create_multi_source_bin:777>: create_multi_source_bin failed
** ERROR: <create_pipeline:1045>: create_pipeline failed
** ERROR: <main:632>: Failed to create pipeline
Quitting
App run failed

And when tried to run Python samples, got below error:

$ python3 deepstream_test_1.py ~/deepstream_sdk_v4.0.2_x86_64/samples/streams/sample_720p.h264

Creating Pipeline 
 
Creating Source 
 
Creating H264Parser 

Creating Decoder 

 Unable to create Nvv4l2 Decoder 
 Unable to create NvStreamMux 
 Unable to create pgie 
 Unable to create nvvidconv 
Creating EGLSink 

Playing file /root/deepstream_sdk_v4.0.2_x86_64/samples/streams/sample_720p.h264 
Traceback (most recent call last):
  File "deepstream_test_1.py", line 263, in <module>
    sys.exit(main(sys.argv))
  File "deepstream_test_1.py", line 196, in main
    streammux.set_property('width', 1920)
AttributeError: 'NoneType' object has no attribute 'set_property'

When I downloaded the docker, install.sh was missing from deepstream sdk folder and I already tried to clear the cache sudo rm ${HOME}/.cache/gstreamer-1.0/registry.x86_64.bin

Please help me to setup deepstream setup at least in this docker image on my Ubuntu 18.04 Desktop.

Thanks,
Archana

26

config_infer_primary.txt is for nvinfer, you should use config source***

27

Ho @Amycao,

I tried below source*** configs, but all have the same output:

deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt

deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt

deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt


No protocol specified
No protocol specified
No protocol specified
No protocol specified
No protocol specified
No protocol specified
** ERROR: <main:651>: Failed to set pipeline to PAUSED
Quitting
App run failed
28

If you not change the config, the output will be onto display, if you not set display environments, the error like this, you can change sink type to 1 Fakesink or 3 File.

[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File
type=1

or

[sink1]
enable=1
type=3

29

Hi @Amycao,

Changing below lines, worked for me.
[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File
type=1

Thanks,
Archana