4400

EdgeBadge TensorFlow Lite for MCUs

Adafruit EdgeBadge TensorFlow Lite for MCUs is a compact board that is credit card-sized. It is powered by the ATSAMD51, with 512KB of flash and 192KB of RAM. It includes 2MB of QSPI flash for file storage, handy for TensorFlow Lite files, images, fonts, sounds, or other assets. A PDM microphone is also on the front as input for micro speech recognition. The Adafruit Arduino library has some demos the user can use to recognize 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 in this area, with many code and process changes. Users can code the EdgeBadge with CircuitPython, MakeCode Arcade, TensorFlow Lite for Microcontrollers/Arduino, and more.