Google Launches Development Board Coral to Build on-device ML products

Spread the love

At Last year’s Google Next conference, in a keynote Google announced that it will launch a development board built around Edge TPU to run machine learning inference at the edge. Almost a year on, the hardware silently launched “into Beta” under the name “Coral” earlier today, and the development board is now available for purchase. The new hardware will officially be announced during the TensorFlow Dev Summit later this week.

Apart from the development board there is Coral USB accelerator is also launched . USB Accelerator is a plug-in USB stick that brings powerful ML inferencing capabilities to existing Linux systems. With the Edge TPU connected over USB 3.0 interface, it allows for quick prototyping of local AI applications.

The Coral development board will help makers to quickly prototype on-device ML products. Scale from prototype to production with a removable system-on-module (SOM) – says Google.

Core Features

Supports TFLite

No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Coral Dev Board.

Scale from prototype to production

Considers your manufacturing needs. The SOM can be removed from the baseboard, ordered in bulk, and integrated into your hardware.

Includes a full system

SOC + ML + Connectivity all on the board running a variant of Linux, so you can run your favourite Linux tools with this board.

Technical Details

CPU NXP i.MX 8M SOC (quad Cortex-A53, Cortex-M4F)
GPU Integrated GC7000 Lite Graphics
ML accelerator Google Edge TPU coprocessor
RAM 1 GB LPDDR4
Flash memory 8 GB eMMC
Wireless Wi-Fi 2×2 MIMO (802.11b/g/n/ac 2.4/5GHz) Bluetooth 4.1
Dimensions 48mm x 40mm x 5mm

Baseboard

Flash memory MicroSD slot
USB Type-C OTG Type-C power Type-A 3.0 host Micro-B serial console
LAN Gigabit Ethernet port
Audio 3.5mm audio jack (CTIA compliant) Digital PDM microphone (x2) 2.54mm 4-pin terminal for stereo speakers
Video HDMI 2.0a (full size) 39-pin FFC connector for MIPI-DSI display (4-lane) 24-pin FFC connector for MIPI-CSI2 camera (4-lane)
GPIO 3.3V power rail 40 – 255 ohms programmable impedance ~82 mA max current
Power 5V DC (USB Type-C)
Dimensions 88 mm x 60 mm x 24mm

Both the development board and the USB accelerator sit on top of Google’s software stack for the Edge TPU. Models need to be developed in TensorFlow Lite rather than TensorFlow, and then compiled to run on the Edge TPU using a web compiler. Some pre-compiled models are also available.

The Coral development board is priced at $149.99, and the USB accelerator is priced at $74.99. Detailed tutorial on how to program and use the board is given here.

Stay Tuned for more updates.

Comments

Spread the love

You may also like...