TensorFlow support for NCS!

[idata]

The Movidius™ Neural Compute Stick is a product designed for developers, we constantly listen to our developers through our online community, project portal and many in-person outreach programs. Your feedback from these events and forum posts help make our product better, so we continue to incorporate these feedback into our software releases. For instance, we enabled raspberry pi support based on the overwhelming feedback we received after we launched at CVPR 2017. One of our latest (and biggest yet) response to our developer feedback is the support for TensorFlow. Since its public launch in 2017, TensorFlow has quickly gained a large following in the machine learning space. The ability to develop and deploy within the same framework is a compelling reason to use the framework, and this is a philosophy we at Movidius also follow at the silicon level. With TensorFlow and Caffe support taken together, we hope that we’ve enabled the broadest swath of developer backgrounds possible with any two frameworks. We look forward to welcoming new TensorFlow users to our community, and enabling our existing users who have been waiting so patiently for this update.

Along with TensorFlow support, NC SDK v1.09.00 contains many new features such as:

1. Tensorflow R1.3 support for tools (only on Ubuntu 16.04 LTS currently).
2. New, unified, faster installer and uninstaller.
3. Now supports complete SDK installation on Raspberry Pi.
4. System installation of tools and API libraries.
5. API support for Python 2.7.
6. Source code included for API, for porting to other architectures or Linux distributions.
7. Tools support for Raspberry Pi.
8. More network support, see documentation for details!
9. Virtual machine support.

Get started with the new SDK at https://developer.movidius.com/start

Visit the release notes for more details about this software release.