Google announced its new hardware products built around its Edge TPU at its Google Next conference last summer. Yesterday, it officially launched the Coral Dev board, a Raspberry-Pi-like board designed to run machine learning algorithms and a USB accelerator.
Coral Development Board
The “Coral Dev Board” has a 40-pin header running Linux on an i.MX8M with an Edge TPU chip for TensorFlow Lite acceleration. The board also has 8GB of eMMC storage, 1GB of LPDDR4 RAM, Wi-Fi, and Bluetooth 4.1. It has USB 2.0/3.0 ports, a 3.5mm audio jack, a DSI display interface, a MIPI-CSI camera interface, an HDMI 2.0a connector, and two PDM digital microphones.
The Coral Dev Board can be used as a single computer when you need accelerated ML processing in a small footprint. It can also be used as an evaluation kit for SOM and for prototyping IoT devices and other similar systems. This board is available for $149.00. Google also announced a 25 MIPI-CSI 5 megapixel camera for the Dev Platform.
USB Accelerator
The USB accelerator is basically a plug-in USB 3.0 stick that adds machine learning capabilities to existing Linux machines. This 65 x 30 mm accelerator can be connected to Linux-based systems via a USB Type-C port. It can also work with a Raspberry Pi at USB 2.0 speeds. The accelerator is built around a 32-bit, 32MHz Cortex-M0+ chip with 16KB of flash and 2KB of RAM.
The USB Accelerator is available for $75.
Developers can build Machine Learning models for both devices in TensorFlow Lite. More information is available on Coral Beta website . They will also soon release a PCI-E accelerator, for integrating the Edge TPU into older systems using a PCI-E interface. Also coming is a complete System-on-Module with CPU, GPU, Edge TPU, Wifi, Bluetooth and Secure Element in a 40mm x 40mm module.
