Coral USB Accelerator

The Coral USB Accelerator brings powerful ML inferencing capabilities to existing Linux systems.

Featuring the Edge TPU —  a small ASIC designed and built by Google— the USB Accelerator provides high performance ML inferencing with a low power cost over a USB 3.0 interface. For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at 100+ fps, in a power efficient manner. This allows you to add fast ML inferencing to your embedded AI devices in a power-efficient and privacy-preserving way.

Models are developed in TensorFlow Lite and then compiled to run on the USB Accelerator.

Edge TPU key benefits

• High-speed TensorFlow Lite inferencing
• Low power
• Small footprint

 Coral is a division of Google, that helps you build intelligent ideas with our platform for local AI.

Features

• Google Edge TPU ML accelerator coprocessor
• USB 3.0 Type-C socket
• Supports Debian Linux on host CPU
• Models are built using TensorFlow
• Fully supports MobileNet and Inception architectures though custom architectures are possible
• Compatible with Google Cloud

Specifications

Edge TPU ML accelerator

• ASIC designed by Google that provides high performance ML inferencing for TensorFlow Lite models

Arm 32-bit Cortex-M0+ Microprocessor (MCU)

•  Up to 32 MHz max
• 16 KB Flash memory with ECC
•  2 KB RAM

Connections

• USB 3.1 (gen 1) port and cable (SuperSpeed, 5Gb/s transfer speed)
• Included cable is USB Type-C to Type-AU

Local inferencing

Run on-device ML inferencing on the Edge TPU designed by Google.

Works with Debian Linux

Connect to any Linux-based system with an included USB Type-C cable.

Supports TensorFlow lite

No need to build models from the ground up. Tensorflow Lite models can be compiled to run on USB Accelerator.