Field Guide · hardware

Also known as: Coral, Edge TPU

Google Coral is a hardware platform built around the Edge TPU, a small AI accelerator that runs machine-learning models locally rather than in the cloud.1

Overview

The Edge TPU is a cut-down tensor processing unit that executes TensorFlow Lite models very efficiently at low power. Coral ships in several forms: a full single-board computer (the Coral Dev Board), a solder-down module, and a USB Accelerator stick that adds the TPU to an existing host such as a Raspberry Pi.2

What it’s for

Coral targets edge AI: on-device vision, audio, and sensor inference where sending data to a server is too slow, too costly, or impossible. It is a more specialised choice than an NVIDIA Jetson — the Edge TPU runs supported quantised models fast and cheap, but it is not a general GPU. In a signal-processing project, a Coral could classify or flag patterns in decoded data at the edge while a Pi handles the radio.

Sources

  1. Edge TPU — Wikipedia, on the Edge TPU at the heart of Coral. 

  2. Coral — Google’s Coral product site, on the Dev Board, modules, and USB Accelerator. 

See also