Co-procesor Google Coral Edge TPU ARM Cortex M0

Coral USB Accelerator, is an edge ML accelerator based on an ASIC chip, designed by Google. It is ideal for use with the Raspberry Pi and Home Assistant, e.g. when recognising objects detected by video surveillance. The module can also be harnessed to work with a custom TensorFlow Lite model compiled into an Edge TPU.

Examples of the interface application can be found on the manufacturer's website: https://coral.ai/examples/ In summary, the device acts as a Edge TPU coprocessor with very low power consumption and a relatively tiny size.

Specifications:

* Accelerator: Edge TPU ML

* Processor: ARM Cortex M0+ 32 bit

* Clocking: up to 32 MHz

* RAM: 2 kB

* Flash memory with ECC: 116 kB

* USB 3.0 type C socket

* Works with systems: Raspberry Pi, Linux, macOS, Windows 10 (in all cases required: USB port, x8664 architecture system, ARM64 with ARMv8 kit)

* Dimensions: 65 x 30 mm

* Included SuperSpeed USB 3.1 type USB-C to USB-A cable