by Adafruit

Image of Board

Machine learning has come to the ‘edge’ - small microcontrollers that can run a very miniature version of TensorFlow Lite to do ML computations.

But you don’t need super complex hardware to start developing your own TensorFlow models! We’ve adapted our popular PyBadge board to add a microphone so you can dip your toes into machine learning waters. It does everything that the PyBadge does, and as we make more projects that use Machine Learning we’ll adapt this board to make it better and better for machine learning.

The EdgeBadge is a compact board - it’s credit card sized. It’s powered by our favorite chip, the ATSAMD51, with 512KB of flash and 192KB of RAM. We add 2 MB of QSPI flash for file storage, handy for TensorFlow Lite files, images, fonts, sounds, or other assets.

We’ve added a PDM microphone on the front as an input for micro speech recognition. Our Arduino library has some demos you can get started with to recognize various word pairs like “yes/no”, “up/down” and “cat/dog”. TensorFlow Lite for microcontrollers is very cutting-edge so expect to see a lot of development happening in this area, with lots of code and process changes.

You can code the EdgeBadge with: CircuitPython, MakeCode Arcade, TensorFlow Lite for Microcontrollers / Arduino, and more!



Have some info to add for this board? Edit the source for this page here.

CircuitPython 4.1.0

This is the latest stable release of CircuitPython that will work with the EdgeBadge.

Start here if you are new to CircuitPython.

Release Notes for 4.1.0

CircuitPython 5.0.0-beta.1

This is the latest unstable release of CircuitPython that will work with the EdgeBadge.

Unstable builds have the latest features but are more likely to have critical bugs.

Release Notes for 5.0.0-beta.1

Absolute Newest

Every time we commit new code to CircuitPython we automatically build binaries for it. They are stored on Amazon S3 by language (some which may be unreleased.) Try them if you want the absolute latest and are feeling risky.

Past Releases

All previous releases are available on GitHub. They are handy for testing but we recommend the latest stable otherwise.