Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5541 Discussions

How can I solve this problem? [ ERROR ] Device with "MYRIAD" name is not registered in the InferenceEngine

DWeiH1
Beginner
679 Views

Run ./classification_sample_async -d MYRIAD -i /Users/tinywolf/intel/openvino/deployment_tools/demo/car.png -m /Users/tinywolf/openvino_models/ir/FP16//classification/squeezenet/1.1/caffe/squeezenet1.1.xml 

 

[ INFO ] InferenceEngine: 

API version ............ 2.0

Build .................. 27579

Description ....... API

[ INFO ] Parsing input parameters

[ INFO ] Parsing input parameters

[ INFO ] Files were added: 1

[ INFO ]  /Users/tinywolf/intel/openvino/deployment_tools/demo/car.png

[ INFO ] Creating Inference Engine

[ ERROR ] Device with "MYRIAD" name is not registered in the InferenceEngine

Error on or near line 238; exiting with status 1

0 Kudos
3 Replies
Sahira_Intel
Moderator
273 Views

Hi DWeiH1,

A couple questions for you:

 

  1. Can you provide more information about the system you're running on? Are you running OpenVINO inside a docker container?
  2. Can you please provide the command you used to convert the model to IR? Did you specify the data type in your command? (FP16 to deploy on Myriad, FP32 to deploy on the CPU)

 

If you would like to use Myriad as your target device, specify it as '-d MYRIAD' in your command to deploy your model.

 

Best Regards,

Sahira

DWeiH1
Beginner
273 Views

Hi Sahira

Thanks

1. I ran demo on MacBook Pro, MacOS Majove 10.14.6

2. The command is "./demo_security_barrier_camera.sh -d MYRIAD"

 

 

 

 

 

 

Sahira_Intel
Moderator
273 Views

Hi DWeiH1,

The current version of the Intel® Distribution of OpenVINO™ toolkit for macOS* supports inference on Intel CPUs only.

https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_macos.html

You can however run a VM (with Ubuntu 16.04) on a host Mac and you should be able to run inference on the NCS/NCS2.

 

Best Regards,

Sahira

Reply