Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Target Movidius at USB port

SSola8
New Contributor I
790 Views

Hi There,

From here, I know that Model Loading and its Inference are performed internally but are there any way I can target a Movidius for my model. I need to distribute the model inference target. I have three models to work with. So on CPU I have loaded all three models on 2 NCS2, taken inference successfully but the same code when running on Raspberry Pi 3B throws NC_ERROR. I am really confused about why that is happening. I need to debug this,  which model is loaded on what devices so that I can know what went wrong. Please help. 

0 Kudos
4 Replies
SuryaPSC_Intel
Employee
790 Views

Hi Saurav,

Can you please confirm that you have followed the instructions to add USB rules for Raspberry Pi.

 

Best Regards,

Surya

0 Kudos
SSola8
New Contributor I
790 Views

Yes, I did.

0 Kudos
SSola8
New Contributor I
790 Views

I solved it. First I plugged-in one NCS2 and let OpenVino, load two models on it and start inferencing and then I plugged the other NCS2 and start the same for the third model. It is running successfully. 

I am still wanna know how that happened internally and can I configure in targeting the loading of models on NCS2? 

Thanks.

0 Kudos
SuryaPSC_Intel
Employee
790 Views

Hi Saurav,

Please refer Multiple NCS devices on OpenVINO.

You may also refer to a similar thread.

 

Best Regards,

Surya

0 Kudos
Reply