Google Coral USB Edge TPU ML Accelerator Coprocessor Raspberry Pi Embedded SBC

Google Coral USB Accelerator

The Coral USB Accelerator brings powerful machine learning (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 low power cost over a USB 3.0 interface. It can execute state-of-the-art mobile vision models, such as MobileNet v2 at 100+ frames per second, in a power-efficient manner, enabling fast ML inferencing for 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.

Key Benefits of Edge TPU

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

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

• Microprocessor (MCU): Arm 32-bit Cortex-M0+ Up to 32 MHz
• Flash Memory: 16 KB with ECC
• RAM: 2 KB
• Connections: USB 3.1 (gen 1) port
• Transfer Speed: SuperSpeed, 5Gb/s
• Included Cable: USB Type-C to Type-A

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