{"id":114652,"date":"2020-07-01T14:07:01","date_gmt":"2020-07-01T12:07:01","guid":{"rendered":"https:\/\/raspberrypi.dk\/produkt\/google-coral-usb-accelerator\/"},"modified":"2026-03-30T13:38:48","modified_gmt":"2026-03-30T11:38:48","slug":"google-coral-usb-accelerator","status":"publish","type":"product","link":"https:\/\/raspberrypi.dk\/en\/product\/google-coral-usb-accelerator\/","title":{"rendered":"Google Coral USB Accelerator"},"content":{"rendered":"
\n
\n
\n
\n
\n
\n

The Coral USB Accelerator adds an Edge TPU coprocessor to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port.<\/p>\n

Performs high-speed ML inferencing<\/i><\/h3>\n

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 400 FPS, in a power efficient manner.\u00a0See more performance benchmarks<\/a>.<\/p>\n

Supports all major platforms<\/i><\/h3>\n

Connects via USB to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10.<\/p>\n

Supports TensorFlow Lite<\/i><\/h3>\n

No need to build models from the ground up.\u00a0TensorFlow Lite<\/a>\u00a0models can be compiled to run on the Edge TPU.<\/p>\n

Supports AutoML Vision Edge<\/i><\/h3>\n

Easily build and deploy fast, high-accuracy custom image classification models to your device with\u00a0AutoML Vision Edge<\/a>.<\/p>\n

Tech specs<\/i><\/h2>\n\n\n\n\n\n
ML accelerator<\/td>\nGoogle Edge TPU coprocessor<\/td>\n<\/tr>\n
Connector<\/td>\nUSB 3.0 Type-C* (data\/power)<\/td>\n<\/tr>\n
Dimensions<\/td>\n65 mm x 30 mm<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

* Compatible with USB 2.0 but inferencing speed is much slower.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/section>\n

\n
\n
\n
\n
\n

Dokumentation<\/i><\/h2>\n
\n

Datasheet<\/i><\/h3>\n