





Any questions? Our AI beta will help you find out quickly.
A USB accessory that enables machine learning inferencing on existing systems. It is compatible with Raspberry Pi and other Linux systems. It performs high-speed ML inferencing: the integrated edge TPU coprocessor can handle 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts per TOPS (2 TOPS per watt). For instance, it can run advanced mobile vision models like MobileNet V2 at 400 FPS efficiently. It works with Debian Linux: it connects to any Debian-based Linux system using the provided USB 3.0 Type-C cable. It supports TensorFlow Lite: there's no need to create models from scratch. TensorFlow Lite models can be compiled for the edge TPU. It supports AutoML Vision Edge: you can readily create and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge. ML Accelerator: Edge TPU coprocessor. Connector: USB 3.0 Type-C (data/power). Dimensions: 65 millimeters x 30 millimeters