SOM System-On-Modules - SOM Google Edge TPU ML Compute Accelerator, Integrate The Edge TPU into Legacy and New Systems Using a Standard Half-Mini PCIe

Description

• 64-bit version of Debian 10 or Ubuntu 16.04 (or newer)
• x86-64 or ARMv8 system architecture
• 64-bit version of Windows 10
• X86-64 system architecture

Performs high-speed ML inferencing
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. See more performance benchmarks.
Works with Debian Linux
Integrates with any Debian-based Linux system with a compatible card module slot.
Supports TensorFlow Lite
No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.
Supports AutoML Vision Edge
Easily build and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge.

Shipping and Returns

• We offer tracked shipping on all orders. Tracking information will be shared as soon as the order is dispatched.
• Please check the delivery estimate before adding a product to the cart. This is displayed for every product on the website.
• Available shipping methods and charges will be displayed at the time of checkout, depending on your exact location.
• All customers are entitled to a return window of 14 days, starting from the date of delivery of the product(s).
• Customers are advised to read our return policy for details of the return process, eligibility, refunds as well as cancellations or exchanges.
• In case of any issues or concerns about Shipping or Returns, please contact us and we will be happy to help.