Introducing the Coral Development Board powered by Google, a single board computer that has been designed for fast on-board machine learning (ML) applications and embedded system design. It features a removable system-on-module (SOM) featuring the Edge TPU coprocessor. 続きを読む
Introducing the Coral Development Board powered by Google, a single board computer that has been designed for fast on-board machine learning (ML) applications and embedded system design. It features a removable system-on-module (SOM) featuring the Edge TPU coprocessor.
The Coral Dev Board is a prototyping development board that can be used to directly develop on board machine learning applications. It is a full computer, with a CPU, GPU and memory with Linux OS. It features a removable system-on-module (SOM) that contains eMMC, SOC, wireless radios and Coral Edge TPU on board.
The Coral Dev Board is ideal for prototyping internet-of-things (IOT) devices and other embedded systems that demand fast on-device ML inferencing. The on-board Edge TPU coprocessor gives the board it’s unique power, capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). The Edge TPU is a small ASIC designed by Google that provides high performance ML inferencing with a low power cost.
Key Features of the Coral Development Board
We love the Google Coral Dev Board, here are some of the highlights of what makes it such an incredible board:
Quickly scale from prototype to production
The SOM is based on NXP’s iMX8M system-on-chip (SOC), but its unique power comes from the Edge TPU coprocessor. scale to production using just the 40 mm × 48 mm SOM board combined with your custom PCB hardware using board-to-board connectors.
Easily add peripherals
The Coral Dev Board has all the IO ports that are needed for the most common applications, so it is SUPER easy to connect accessories for projects. The ports include:
Ready made AI models to use
No need to build models from the ground up as TensorFlow Lite models can be compiled to run on the Edge TPU. Allowing for fast prototyping on your devices.
Part of the Google Coral Platform Range
The Coral range is a fantastic platform powered by Google that allows for high speed prototyping to production, with hardware components that bring high performance ML capabilities onto the edge devices and a complete set of software tools to develop ML models and applications. Coral also offers a set of ready to use ML models. Be sure to check out the full portfolio.
|CPU||NXP i.MX 8M SoC (quad Cortex-A53, Cortex-M4F)|
|GPU||Integrated GC7000 Lite Graphics|
|ML accelerator||Google Edge TPU coprocessor: 4 TOPS (int8); 2 TOPS per watt|
|RAM||1 GB LPDDR4 (option for 2 GB or 4 GB coming soon)|
|Flash memory||8 GB eMMC, MicroSD slot|
|Wireless||Wi-Fi 2×2 MIMO (802.11b/g/n/ac 2.4/5GHz) and Bluetooth 4.2|
|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|