Tutorial STEP BY STEP
(^58) July 2018 raspberrypi.org/magpi
USE
TENSORFLOW
ON RASPBERRY PI
Discover how to install and use Google’s TensorFlow framework
to learn AI techniques and add AI to your future projects
oogle TensorFlow is a powerful open-source
software framework used to power AI projects
around the globe.
TensorFlow is used for machine learning and the
creation of neural networks. These make it possible
for computers to perform increasingly complex tasks,
such as image recognition and text analysis.
When it comes to AI, most people think of powerful
supercomputers crunching billions of numbers
in giant databanks. But there are two parts to
machine learning. There is a train/test part, where
you use a lot of data to build a model. And there’s
G
Raspbian
1GB USB stick
16GB microSD
card
TensorFlow
You’ll
Need
LUCY HATTERSLEY
Lucy is the editor of The MagPi
magazine and a general coding spod.
We all know she’s secretly trying to
build Twiki from Buck Rogers.
magpi.cc
deployment, where you take a model and use it as
part of a project. And that’s where the Raspberry
Pi fits in.
Although Raspberry Pi isn’t officially supported by
Google, there are example models included for the
Raspberry Pi and it can be fun (if a bit hacky) to get
TensorFlow up and running on a Pi. And there are lots
of interesting community projects around that put
TensorFlow to good use.
Using TensorFlow can give you a good
understanding of how AI works, and how to put AI
to practical use in your projects.
TensorFlow Playgrounds is a website
that visualises deep neural networks.
It’s a good place to visit to understand
some of the underlying concepts of
artificial intelligence
This model is being used to fit blue
and orange dots in an image. The
more complex the layout of dots, the
more layers the network needs (along
with better activation functions).
TensorFlow Playgrounds helps you
understand these concepts