Coral USB Accelerator

Author : Google Published Time : 2019-03-11
Coral USB Accelerator brings powerful ML (machine learning) 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 fast ML inferencing to embedded AI devices in a power-efficient and privacy-preserving way.

Features

Google Edge TPU ML accelerator coprocessorUSB 3.0 Type-C socketSupports Debian Linux on host CPUModels are built using TensorFlow
Fully supports MobileNet and Inception architectures though custom architectures are possibleCompatible with Google Cloud

Specifications

Arm 32-bit Cortex-M0+ Microprocessor (MCU)
Up to 32 MHz max16 KB Flash memory with ECC2 KB RAMConnections
USB 3.1 (gen 1) port and cable (SuperSpeed, 5Gb/s transfer speed)Included cable is USB Type-C to Type-A
Google Newest

Coral Environmental Sensor Board is an add-on board for the Coral Dev Board or Raspberry Pi to add sensing capabilities.

Date: 2019-04-12

Coral Camera is a 5-megapixel camera module that's compatible with the Coral Dev Board. Connects through the MIPI-CSI interface, and provides an easy way to bring visual input into your models.

Date: 2019-04-04

Coral Dev Board is a single-board computer with an Edge TPU system-on-module (SOM).

Date: 2019-03-11

Google Coral TBU USB Accelerator has a USB Type-C socket that connects to any Linux-based system to perform accelerated ML (Meta Language) inferencing.

Date: 2019-03-11

Google AIY Vision Kit is a do-it-yourself kit that creates a machine-learning camera that recognizes objects, Raspberry Pi powered.

Date: 2019-01-09

Google AIY Voice Kit is a do-it-yourself intelligent speaker project, experiment with voice recognition and the Google Assistant.

Date: 2019-01-09