A development board to quickly prototype on-device ML products. Scale from prototype to production with a removable system-on-module (SOM).
This product has shipping restriction to certain countries. It can only be sent to countries and regions listed as below: Austria , Belgium , Bulgaria , Croatia , Cyprus , Denmark , Estonia , Finland , Germany , Greece , Hong Kong, Hungary , Iceland , Ireland , Italy , Latvia , Liechtenstein , Lithuania , Luxembourg , Malta , Netherlands , Norway , Poland , Portugal , Romania , Slovakia , Slovenia , Spain , Sweden , Switzerland , Turkey , United Kingdom , US
We have released the Coral Dev Board TELEC Version which can be sent to Japan and Korea.
The Coral Dev Board is a single-board computer with a removable system-on-module (SOM) that contains eMMC, SOC, wireless radios, and Google’s Edge TPU. It’s perfect for IoT devices and other embedded systems that demand fast on-device ML inferencing.
You can use the Dev Board as a single-board computer for accelerated ML processing in a small form factor, or as an evaluation kit for the SOM that’s on-board. The 40 mm × 48 mm SOM on the Dev Board is available at volume. It can be combined with your custom PCB hardware using board-to-board connectors for integration into products.
The SOM is based on NXP's iMX8M system-on-chip (SOC), but its unique power comes from the Edge TPU coprocessor. The Edge TPU is a small ASIC designed by Google that provides high performance ML inferencing with a low power cost. For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at 100+ fps, in a power efficient manner.
Edge TPU key benefits
- High-speed TensorFlow Lite inferencing
- Low Power
- Small footprint
The baseboard includes all the peripheral connections you need to prototype a project, including USB 2.0/3.0 ports, DSI display interface, CSI2 camera interface, Ethernet port, speaker terminals, and a 40-pin GPIO header.
Coral is a division of Google, that helps you build intelligent ideas with our platform for local AI.
- NXP i.MX 8M SOC (Quad-core Cortex-A53, plus Cortex-M4F)
- Google Edge TPU ML accelerator coprocessor
- Cryptographic coprocessor
- Wi-Fi 2x2 MIMO (802.11b/g/n/ac 2.4/5GHz)
- Bluetooth 4.1
- 8GB eMMC
- 1GB LPDDR4
- USB Type-C power port (5V DC)
- USB 3.0 Type-C OTG port
- USB 3.0 Type-A host port
- USB 2.0 Micro-B serial console port
- 3.5mm audio jack (CTIA compliant)
- Digital PDM microphone (x2)
- 2.54mm 4-pin terminal for stereo speakers
- HDMI 2.0a (full size)
- 39-pin FFC connector for MIPI-DSI display (4-lane)
- 4-pin FFC connector for MIPI-CSI2 camera (4-lane)
MicroSD card slots
Gigabit Ethernet ports
40-pin GPIO expansion headers
Supports Debian Linuxs
Models are built using TensorFlow
Fully supports MobileNet and Inception architectures though custom architectures are possible
Compatible with Google Cloud
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.
|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||1 GB LPDDR4|
|Flash memory||8 GB eMMC|
|Wireless||Wi-Fi 2x2 MIMO (802.11b/g/n/ac 2.4/5GHz) Bluetooth 4.1|
|Dimensions||48mm x 40mm x 5mm|
|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
1 x Coral Dev Board
LEARN AND DOCUMENTS
SHARED BY USERS
It's really cool!I'm a novice Linux/raspberry pi user and I've been playing with this for a few days with great success. So far I've been able to get all of the demos to work without much issue. I've also reflashed the board from an SD card, changed the local host name, moved mdt keys around to different machines, use the serial console, the mendel dev tools over USB and logged in remotely with ssh. I had to do a minimal amount of work arounds (compared to raspberry pi and other linux) to get things working. There are definitely some missing bits of info in the getting started guide, but I was able to figure them all out eventually. You NEED a 64bit OS to build the mendel dev tools, and you need those unless you are a linux superuser and know your way around the file system and can really get into the OS and customize things. IE, you have to use the MDT to push over an SSH key and you can't connect to the board over USB through MDT without a 64bit OS. Also, they recommend using SCREEN for the serial console, but you have to add your user to the dialout group in order to get SCREEN to work (that step was not in the getting started guide). I changed the name of my board (it auto generates a random name) using the built in GUI but it was not changed in the LOCALHOSTS file which caused problems with other packages that I wanted to install. Little things like that. Overall, it's really cool, and I'm having fun getting started with it.
works great!After a few weeks with this board I have been really struggling to find any community of users that are actually developing with this. There is very little support or examples available and the board does not support a lot of the most common AI frameworks and libraries. I was not originally aware that TensorFlow Lite is a Google proprietary framework and is not supported by the greater AI community. I switched to Jetson Nano as there is a huge amount of support, examples, and projects available and it supports all of the AI code and frameworks that you could possibly want.
works wellSo far works well, good board!
KimNice board, works well, great evaluation board from Google...
RutledgeGreat evaluation board from Google, I saw there are a few others on Amazon that are priced higher from third parties. This is the real one from Google.