TensorFlow Lite for Microcontrollers

The TensorFlow Lite for Microcontrollers Experiments collection features work by developers who are experimenting with TensorFlow Lite for Microcontrollers. These projects combine Arduino and TensorFlow to create awesome experiences and useful tools. You can find helpful links throughout the site for creating your own experiments and explore resources.


When we launched the TensorFlow Microcontoller Challenge, we invited developers to push the boundaries of TensorFlow Lite for Microcontrollers. We want to send a big thank you to everyone who participated for their incredibly inspiring submissions. And a huge congratulations to our five winners!

Mapping Dance

by Eduardo PadrĂ³n
Take control of lighting and video projections with your dance moves.


by Eunji Lee, Jueun Choi, Yeonhee Kim, Jonghyun Baek, Yongjae Kim
Stay active, using movement to control a variety of games.

Snoring Guardian

by Naveen Kumar
A snore-no-more device embedded in your pillow.

Squats Counter

by Manas Pange
Focus on your form, while this tracker counts your squats.

Voice Turn

by Alvaro Gonzalez-Vila
A safer way for cyclists to signal using their voice.


Air Snare

by Google Creative Lab
Play an invisible drum kit.

Finger User Interface

by Google Creative Lab
Control your devices with the wave of a finger.

Tiny Motion Trainer

by Google Creative Lab
A code-free tool that lets you create custom, microcontroller-ready models based on IMU data.


by Google Creative Lab
Draw shapes in the sky to form constellations.

Morning Mountain: Visual Alarm Clock

by Google Creative Lab
Get up in the morning by striking a pose to stop your alarm from ringing.