Google Coral Dev Board

The Google Coral Dev Board is a single-board computer that's ideal when you need to perform fast machine learning (ML) inferencing in a small form factor.

The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS, in a power efficient manner.

A single-board computer with SoC + ML + wireless connectivity, all on the board running a derivative of Debian Linux we call Mendel, so you can run your favorite Linux tools with this board.

There is no need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU. Easily build and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge.

You can use the Dev Board to prototype your embedded system and then scale to production using the on-board Coral System-on-Module (SoM) combined with your custom PCB hardware. The SoM can be removed from the baseboard, ordered in bulk, and integrated into your hardware.

Model Overview