The Google Coral USB Accelerator adds a co-processor to your Edge TPU system that enables high-speed machine learning inference on a wide range of systems, simply by plugging it into a USB port.
Performs high-speed ML inference
The integrated Edge TPU coprocessor is capable of 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts per TOPS (2 TOPS per watt). For example, it can run state-of-the-art mobile vision models such as MobileNet v2 at nearly 400 FPS in a power-efficient manner.
It supports all major platforms
Connects via USB to any system running Debian Linux (including Raspberry Pi), macOS or Windows 10.
Supports TensorFlow Lite
No need to build models from scratch. TensorFlow Lite models can be compiled to run on the Edge TPU. There is no need to build models from scratch. TensorFlow Lite models can be compiled to run on the Edge TPU.
|ML Accelerator||Google Edge TPU coprocessor:|
4TOPS(int8); 2 TOPS per watt
|Connector||USB 3.0 Type-C* (data/power)|
|Dimensions||65mm x 30mm|
|Availability||Australia, European Union (except France, Czech Republic), Ghana, Hong Kong, India, Indonesia, Israel, Japan, Kenya, Malaysia, New Zealand, Oman, Philippines, Singapore, South Korea, Taiwan, Thailand, United States, Vietnam|
* Compliant with USB 2.0, but the derivation speed is slower.