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.
6404 Discussions

Transfer learned Tensorflow Mobilenet_SSD & Raspberry Pi 3B+ & NCS 2

idata
Employee
‎03-20-2019 02:14 PM
689 Views

Hey everyone,

 

as the title stated I want to transferlearn a Mobilenet SSD with my own dataset on tensorflow(don't care if .json or .pb)and get it running on a Pi 3B+ using 2 NCS2.

 

But I'm a bit lost as where to start and can't find a proper tutorial or anything.

 

managed to install OpenVINO on my pi, but how do I get my MnSSD running with OpenVino and the NCS2?

 

Any help wanted ;)

0 Kudos

Link Copied

1 Reply
idata
Employee
‎03-22-2019 06:58 PM
377 Views

Hi @Tonto5000 ,

 

Thanks for reaching out. I think what you are looking for is on how to convert a Tensorflow* Model using the Model Optimizer, you can find the tutorial here . I am not sure if the Model Optimizer is available for the Raspberry Pi version of the OpenVINO toolkit, my guess is that you may have to convert your Tensorflow* model using a non-Raspbian version of OpenVINO (i.e. on Windows or Linux) and then transfer the resulting IR to the Raspberry Pi. Hope this helps, let me know if you have additional questions.

 

Regards,

 

@Luis_at_Intel
0 Kudos
Copy link
Reply

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.