Coral USB Accelerator

The Coral USB Accelerator is a powerful USB accessory designed to enhance machine learning inferencing on existing systems, seamlessly integrating with devices like Raspberry Pi and other Linux-based platforms.

Key Features

• High-Speed ML Inferencing:

  • Equipped with an on-board Edge TPU Coprocessor, the Coral USB Accelerator can perform an astonishing 4 trillion operations per second (TOPS), using just 0.5 watts per TOPS (equivalent to 2 TOPS per watt).
  • Capable of executing state-of-the-art mobile vision models, such as MobileNet V2, at an impressive 400 FPS, all while maintaining energy efficiency.

• Compatibility with Debian Linux:

  • Easily connects to any Debian-based Linux system using the included USB 3.0 Type-C cable.

• Support for TensorFlow Lite:

  • Simplifies the development process by allowing you to compile TensorFlow Lite models to run on the Edge TPU, eliminating the need to build models from scratch.

• Automated Model Development with AutoML Vision Edge:

  • Streamline the creation and deployment of fast, high-accuracy custom image classification models to your device, utilizing AutoML Vision Edge.

Technical Specifications

• Machine Learning Accelerator: Google Edge TPU Coprocessor
• Connector Type: USB 3.0 Type-C (for data and power)
• Dimensions: 65 mm x 30 mm

Enhance your machine learning capabilities with the Coral USB Accelerator and unlock the power of efficient inference on your projects!