OPENVINO error in demo Neural Computer Stick

[Olivero__Alberto]

I have OPENVINO installed from l_openvino_toolkit_p_2018.5.455.tgz

UBUNTU 18.04

Intel CPU gen 7

Neural Computer Stick 2

I installed following https://software.intel.com/en-us/articles/OpenVINO-Install-Linux and the next steps needed for the USB stick  from https://software.intel.com/en-us/neural-compute-stick/get-started.

The first demo (./demo_security_barrier_camera.sh -d MYRIAD) is working properly I see the picture.

In the second demo I got the following error.

[setupvars.sh] OpenVINO environment initialized

alberto@alberto-i7-pc:~/inference_engine_samples/intel64/Release$ ./security_barrier_camera_demo -i ~/intel/computer_vision_sdk/deployment_tools/demo/car_1.bmp -d MYRIAD -m ~/intel/computer_vision_sdk/deployment_tools/intel_models/vehicle-license-plate-detection-barrier-0106/FP16/vehicle-license-plate-detection-barrier-0106.xml -d_va MYRIAD -m_va ~/intel/computer_vision_sdk/deployment_tools/intel_models/vehicle-attributes-recognition-barrier-0039/FP16/vehicle-attributes-recognition-barrier-0039.xml -d_lpr MYRIAD -m_lpr ~/intel/computer_vision_sdk/deployment_tools/intel_models/license-plate-recognition-barrier-0001/FP16/license-plate-recognition-barrier-0001.xml
[ INFO ] InferenceEngine:
    API version ............ 1.4
    Build .................. 19154
[ INFO ] Parsing input parameters
[ INFO ] Capturing video streams from the video files or loading images
[ WARNING ] File /home/alberto/intel/computer_vision_sdk/deployment_tools/demo/car_1.bmp cannot be opened!
[ INFO ] Number of input image files: 0
[ INFO ] Number of input video files: 0
[ INFO ] Number of input channels:    0
Eccezione in virgola mobile (core dump creato)

In the third demo I got the following error also if  I downloaded the model following the instruction (alberto@alberto-i7-pc:/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_downloader$ sudo python3 downloader.py --name face-detection-retail-0004-fp16).

[setupvars.sh] OpenVINO environment initialized

alberto@alberto-i7-pc:~/inference_engine_samples/intel64/Release$ ./interactive_face_detection_demo -d MYRIAD -m ~/intel/computer_vision_sdk/deployment_tools/intel_models/face-detection-retail-0004/FP16/face-detection-retail-0004.xml -d_ag MYRIAD -m_ag ~/intel/computer_vision_sdk/deployment_tools/intel_models/age-gender-recognition-retail-0013/FP16/age-gender-recognition-retail-0013.xml -d_em MYRIAD -m_em ~/intel/computer_vision_sdk/deployment_tools/intel_models/emotions-recognition-retail-0003/FP16/emotions-recognition-retail-0003.xml -d_hp MYRIAD -m_hp ~/intel/computer_vision_sdk/deployment_tools/intel_models/head-pose-estimation-adas-0001/FP16/head-pose-estimation-adas-0001.xml
InferenceEngine:
    API version ............ 1.4
    Build .................. 19154
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading plugin MYRIAD

    API version ............ 1.5
    Build .................. 19154
    Description ....... myriadPlugin
[ INFO ] Loading network files for Face Detection
[ ERROR ] Error loading xmlfile: /home/alberto/intel/computer_vision_sdk/deployment_tools/intel_models/face-detection-retail-0004/FP16/face-detection-retail-0004.xml, File was not found at line: 1 pos: 0

[Cary_P_Intel1]

Hi, Alberto,

I tested on my Ubuntu, the only difference is i use 16.04. I didn't encounter your error, can you check if the intel_models are really inside the path you used in command? Since from the error, it's not related to model itself but can't find the file

[Olivero__Alberto]

Hi I SOLVED keeping OPENVINO working in UBUNTU 18.04,

I report below the work-around I did (very simple for Linux user) to keep it working for the benefit of other users.

1) general comment in the Instal tutorial is reported multiple times that the path where files are stores in "/opt/intel/computer_vision" but in my case it was "/opt/intel/computer_vision_sdk" so need to be modified manually

2) in the folder home/intel there is not a link to opt/intel folder, so I created it manually

3) to keep working the third example using "interactive_face_detection_demo" it is needed at first to move in ~/inference_engine_samples/interactive_face_detection_demo  running the make file so that the "interactive_face_detection_demo" will be created