Development board `` Google Coral Dev Board '' with Google Edge TPU

2019/6/10 TEGARA Co., Ltd. engineering, Artificial intelligence, Robotics, Development kit / electronic work, Overseas Products What's New (Unipos)
■ This is an article posted on June 2019, 6, so the content of the information may be out of date.

Development board equipped with Google Edge TPU on Unipos websiteGoogle Coral Dev Board Page has been added.

Coral Dev BoardIs a single board computer with Google Edge TPU (Tensor Processing Unit) for edge devices such as IoT. SoM (System on Module) allows you to prototype on-device machine learning inference applications.

Advantages of Edge TPU:
・ TensorFlow Lite support (short time inference on device)
・ Low power
・ Space saving

[Example of products handled]

■ Coral Dev Board
A small computer that integrates NXP Semiconductors' i.MX 8M into one board, including Google Edge TPU, USB 1 / 2.0 port, DSI (Display Serial Interface), CSI-3.0 (Camera Serial Interface), etc. , Has multiple interfaces required for product development.

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

Baseboard
– Flash memory: MicroSD slot
– USB: Type-C OTG Type-C power Type-A 3.0 host Micro-B serial console
– LAN: Gigabit Ethernet
– Audio: 3.5mm ayduo jack / 4 pin stereo terminal
– Video: HDMI 2.0a (full size)
– GPIOs: 3.3V
– Power: 5V DC (USB Type-C)
– Dimensions: 88 x 60 x 24 (mm)

Supported OS: Mendel Linux (derivative of Debian)
Supported Frameworks: TensorFlow Lite
Languages: Python and C ++

-Maker page FAQFor detailed information, see.

■ Coral USB Accelerator
It is a USB Accelerator for machine learning that runs on Raspberry Pi and Linux computers.
Connecting an Edge TPU designed for inference at Google's edge to a supported Linux computer makes it easy to perform ML inference on your device.

【Main Specifications】
ML accelerator: Google Edge TPU coprocessor
Connector: USB Type-C * (data / power)
Dimensions: 65 x 30 (mm)
Operating Systems: Debian Linux

* Compatible with Raspberry Pi boards at USB 2.0 speeds only.

 

■ Click here for product details and inquiries
Development board with Coral Dev Board / Google Edge TPU
Manufacturer (Coral / Developer Google LLC.) Website

People who read this article also read this article