Arduino Tiny Machine Learning Kit
Ever wondered how to build a small intelligent device that reacts to sounds like a keyword being spoken, recognizes gestures like waving a magic wand, or even recognize faces? With this kit combined with the power of Tiny Machine Learning (TinyML) you can do all of that and much more! We want to show you how these possibilities can be part of your own tiny smart device!
Overview
The Tiny Machine Learning Kit, combined with the exciting TinyML Applications and Deploying TinyML on Microcontrollers courses that are part of the Tiny Machine Learning (TinyML) specialization from EdX will equip you with all the tools you need to bring your ML visions to life!
The kit consists of a powerful board equipped with a microcontroller and a wide variety of sensors (Arduino Nano 33 BLE Sense*). The board can sense movement, acceleration, rotation, barometric pressure, sounds, gestures, proximity, color, and light intensity. The kit also includes a camera module (OV7675) and custom Arduino shield to make it easy to attach your components and create your very own unique TinyML project. You will be able to explore practical ML use cases using classical algorithms as well as deep neural networks powered by TensorFlow Lite Micro. The possibilities are limited only by your imagination!
“The Future of Machine Learning is Tiny and Bright. We’re excited to see what you’ll do!”
Prof. Vijay Janapa Reddi, Harvard University and Pete Warden, Google
*For us to be able to have this kit back in stock we produced a Nano 33 BLE Sense without the HTS221 sensor (temperature and humidity), this change does not affect this kit’s usage and/or content experience. This board is fully compatible with the kit’s documentation.
Tech specs
The Tiny Machine Learning Kit includes:
- 1 Arduino Nano 33 BLE Sense board
- 1 OV7675 Camera
- 1 Arduino Tiny Machine Learning Shield
- 1 USB A to Micro USB Cable
Conformities
Resources for Safety and Products
Manufacturer Information
The production information includes the address and related details of the product manufacturer.
Arduino S.r.l.
Via Andrea Appiani, 25
Monza, MB, IT, 20900
https://www.arduino.cc/
Responsible Person in the EU
An EU-based economic operator who ensures the product's compliance with the required regulations.
Arduino S.r.l.
Via Andrea Appiani, 25
Monza, MB, IT, 20900
Phone: +39 0113157477
Email: support@arduino.cc
Documentation
Get Inspired
Begins a process of combining Portenta H7 with Vision Shield – LoRa by acquiring, sending, and displaying a camera image via USB/Serial connection.
Jeremy Ellis is a teacher, and as such, wanted a longer-term project that his students could do to learn more about microcontrollers and computer vision/machine learning, and what better way is there than a self-driving car. His idea was to take an off-the-shelf RC car which uses DC motors, add an Arduino Portenta H7 as the MCU, and train a model to recognize target objects that it should follow. After selecting the “RC Pro Shredder” as the platform, Ellis implemented a VNH5019 Motor Driver Carrier, a servo motor to steer, and a Portenta H7 + Vision Shield along with a 1.5” OLED module. After 3D printing a small custom frame to hold the components in the correct orientation, nearly 300 images were collected of double-ringed markers on the floor. These samples were then uploaded to Edge Impulse and labeled with bounding boxes before a FOMO-based object detection model was trained. Rather than creating a sketch from scratch, the Portenta community had already developed one that grabs new images, performs inferencing, and then steers the car’s servo accordingly while optionally displaying the processed image on the OLED screen. With some minor testing and adjustments, Ellis and his class had built a total of four autonomous cars that could drive all on their own by following a series of markers on the ground. For more details on the project, check out Ellis' Edge Impulse tutorial here.