The Raspberry Pi board developers can now make use of the latest TensorFlow 1.9 features to build their board projects. Most developers use Raspberry Pi for shaping their innovative DIY projects. The Pi also acts as a pathway to introduce people to programming with an added benefit of coding in Python.
The main objective of blending TensorFlow with the Raspberry Pi board is to let people explore the capabilities of machine learning on cost-effective and flexible devices.
Eben Upton, the founder of the Raspberry Pi project, says, “It is vital that a modern computing education covers both fundamentals and forward-looking topics. With this in mind, we’re very excited to be working with Google to bring TensorFlow machine learning to the Raspberry Pi platform. We’re looking forward to seeing what fun applications kids (of all ages) create with it.”
By being able to use TensorFlow features, existing users, as well as new users, can try their hand on live machine learning projects. Here are few real-life examples of Tensorflow on Raspberry Pi:
DonkeyCar platform
DonkeyCar, a platform to build DIY Robocars, uses TensorFlow and the Raspberry Pi to create self-driving toy cars.
Object Recognition Robot
The Tensorflow framework is useful for recognizing objects. This robot uses a library, a camera, and a Raspberry Pi, using which one can detect up to 20,000 different objects.
Waste sorting robot
This robot is capable of sorting every piece of garbage with the same precision as a human. This robot is able to recognize at least four types of waste. To identify the category to which it belongs, the system uses TensorFlow and OpenCV.
One can easily install Tensorflow from the pre-built binaries using Python pip package system from the pre-built binaries. One can also install it by simply running these commands on the Raspbian 9 (stretch) terminal:
sudo apt install libatlas-base-dev
pip3 install tensorflowRead more about this project on GitHub page
Read Next
5 DIY IoT projects you can build under $50