Google Coral- USB Accelerator

USB Accelerator

A USB accessory that brings machine learning inferencing to existing systems. Works with Raspberry Pi and other Linux systems.







Features

• Google Edge TPU ML accelerator coprocessor
• USB 3.0 Type-C socket
• Supports Debian Linux on host CPU

Overview

The Coral USB Accelerator is a USB device that adds an Edge TPU coprocessor to your system. It includes a USB socket so you can connect it to any Linux-based system to perform accelerated ML inferencing.

The onboard Edge TPU is a small ASIC designed by Google that provides high-performance ML inferencing with a low power cost. For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at 100+ fps, in a power efficient manner.

System requirements

The Coral USB Accelerator must be connected to a host computer with the following specifications:

• Any Linux computer with a USB port
• Debian 6.0 or higher, or any derivative thereof (such as Ubuntu 10.0+)
• The system architecture of either x86_64 or ARM64 with ARMv8 instruction set

Software and operation

The USB Accelerator doesn't require any software installed, but the host computer to which it's attached must install the Edge TPU runtime and API library. For instructions, see the Get Started guide.

For information about how to create models and run inferences the Edge TPU, read TensorFlow models on the Edge TPU.