03-20-2019 02:14 PM
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 ;)
03-22-2019 06:58 PM
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.