The Google Coral USB Accelerator is a device that adds an Edge TPU coprocessor to your system, allowing for high-speed machine learning inferencing on various systems through a simple USB connection. This on-board Edge TPU coprocessor can perform up to 4 trillion operations per second (TOPS) while using only 0.5 watts per TOPS, providing power-efficient performance. Furthermore, there is no need to create models from scratch as TensorFlow Lite models can be compiled to run on the Edge TPU, enabling users to execute advanced mobile vision models such as MobileNet v2 at almost 400 FPS.
Disclosure: This post contains affiliate links. If you click through and make a purchase, I will earn a commission, at no additional cost to you. Read my full disclosure here.