Error when running demo when installing Openvino on Raspberry Pi

[Zheng__Martin]

Hello,

I installed according to the tutorial  on the official website(https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html).

The installation and configuration is complete. When running the following test:

./armv7l/Release/object_detection_sample_ssd -m face-detection-adas-0001.xml -d MYRIAD -i test.jpg

I got the error:

[ INFO ] InferenceEngine:
        API version ............ 2.1
        Build .................. custom_releases/2020/1_d349c3ba4a2508be72f413fa4dee92cc0e4bc0e1
        Description ....... API
Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     test.jpg
[ INFO ] Loading Inference Engine
[ INFO ] Device info:
        MYRIAD
        myriadPlugin version ......... 2.1
        Build ........... 37988
[ INFO ] Loading network files:
        face-detection-adas-0001.xml
        face-detection-adas-0001.bin
[ ERROR ] Check 'axis < static_cast<size_t>(input_rank)' failed at /teamcity/work/scoring_engine_build/releases_2020_1/ngraph/src/ngraph/op/gather.cpp:140:
While validating node 'Gather[Gather_852](patternLabel_848: float{10,20,30}, patternLabel_849: int64_t{5}, patternLabel_851: int64_t{1}) -> (??)':
The axis must => 0 and <= input_rank (axis: 4294967295).

[jain__Yasha]

I also got the same error did you find a solution?

However the opencv verison works properly. 

[David_C_Intel]

Hi Martin and Yasha,

Thank you for reaching out.

This is a known issue with the latest OpenVINO™ toolkit version (2020.1). The "axis" error is caused by the new IR v10 format. 

Try using the pre-trained model from the previous release:

wget https://download.01.org/opencv/2019/open_model_zoo/R3/20190905_163000_models_bin/face-detection-retail-0004/FP16/face-detection-retail-0004.bin

https://download.01.org/opencv/2019/open_model_zoo/R3/20190905_163000_models_bin/face-detection-retail-0004/FP16/face-detection-retail-0004.xml

If you are using the full installation of OpenVINO toolkit to optimize your own model. Add the following flag to the model optimizer command to generate the previous version of IR format.

--generate_deprecated_IR_V7

Best regards,

David