DeepStream NGC Container Issues

Hey everyone, so I am starting to play around with the DeepStream SDK and am trying to run some of the samples per the documentation. When running a sample application from a docker container on a remote server I receive the following errors. Any insight into this would be greatly appreciated.

Command:

deepstream-app -c configs/deepstream-app/config_infer_secondary_carmake.txt

Error:

(deepstream-app:19): GStreamer-CRITICAL **: 16:57:38.207: gst_element_get_static_pad: assertion ‘GST_IS_ELEMENT (element)’ failed
Segmentation fault (core dumped)

Documentation:

Running the samples

  1. Go to samples directory and run
    deepstream-app -c
  2. Application config files included in configs/deepstream-app/
    a. source30_1080p_dec_infer-resnet_tiled_display_int8.txt (30 Decode + Infer)
    b. source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
    (4 Decode + Infer + SGIE + Tracker)
    c. source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt
    (4 Decode + Infer + SGIE + Tracker executed on gpu1)
  3. Configuration files for “nvinfer” element in configs/deepstream-app/
    a. config_infer_primary.txt (Primary Object Detector)
    b. config_infer_secondary_carcolor.txt (Secondary Car Color Classifier)
    c. config_infer_secondary_carmake.txt (Secondary Car Make Classifier)
    d. config_infer_secondary_vehicletypes.txt (Secondary Vehicle Type Classifier)

Notes:

  1. If the application runs into errors, cannot create gst elements, try again
    after removing gstreamer cache
    rm ${HOME}/.cache/gstreamer-1.0/registry.x86_64.bin