The Coral USB Accelerator adds an Edge TPU coprocessor to your system, allowing you to perform high-speed machine learning inferences on a wide range of devices by simply plugging it into a USB port.
High-speed ML inference
The integrated Edge TPU coprocessor can perform 4 trillion operations per second (TOPS), with a power consumption of only 0.5 watts per TOPS (or 2 TOPS per watt). For example, it can run advanced computer vision models such as MobileNet v2 at nearly 400 frames per second in a highly energy-efficient manner. See the full benchmarks for more details on performance.
Compatibility with 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 create models from scratch: TensorFlow Lite models can be compiled to run on the Edge TPU.
Specifications:
- ML accelerator: Google Edge TPU coprocessor: 4 TOPS (with int8 operations) / 2 TOPS per watt
- Connector: USB 3.0 Type-C (for data and power)
- Dimensions: 65 mm x 30 mm
- Compatibility: Compatible with USB 2.0, but with reduced inference speed
Package contains: 1 x Coral USB Accelerator
