Guide for new users

[idata]

Hi there,

New to Movidius so I need some help ;)

Tried to search for a good starting place but didn't find a good place to start.

What I would like to know is a short quick guide of building a DNN in Tensorflow, don't need to do anything fancy just so I know how I should do that.

How to train that network and how to transfer that to the stick to get some work done.

If there is a good starting point allready then point me in that direction.

/Henke

[idata]

@port513 AshwinVijayaKumar has a blog that might fit what you are looking for @ https://movidius.github.io/blog/deploying-custom-caffe-models/

[idata]

@port513, in addition to what @Tome_at_Intel recommended, below are a few TensorFlow related tutorials:

Simple single-conv model - https://github.com/ashwinvijayakumar/ncappzoo/blob/single-conv/tensorflow/single-conv/README.md

Pre-trained TF inception models - https://github.com/ashwinvijayakumar/ncappzoo/blob/tensorflow-template/tensorflow/inception/README.mdPre-trained TF MobileNet models - https://github.com/ashwinvijayakumar/ncappzoo/blob/tensorflow-template/tensorflow/mobilenets/README.md

At the time of writing this response, I haven't yet merged my image-classifier updates, so replace apps/image-classifier with https://github.com/ashwinvijayakumar/ncappzoo/tree/classifier-template/apps/image-classifier before following instructions on tensorflow/single-conv/README.md