G650-04686-01 Coral M.2 Accelerator B+M Key

Description

• 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.
• 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.

The Coral M.2 Accelerator is an M.2 module that brings the Edge TPU coprocessor to existing systems and products. The Edge TPU is a small ASIC designed by Google that provides high performance ML inferencing with low power requirements: it's 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 almost 400 FPS, in a power efficient manner. This on-device processing reduces latency, increases data privacy, and removes the need for constant high-bandwidth connectivity. The M.2 Accelerator is a dual-key M.2 card (either A+E or B+M keys), designed to fit any compatible M.2 slot. This form-factor enables easy integration into ARM and x86 platforms so you can add local ML acceleration to products such as embedded platforms, mini-PCs, and industrial gateways. AI-enabled NVR system If you are planning to use Coral M.2 B+M Accelerator for Home Assistant of home automation applications, we recommend Odyssey Blue, an Intel Celeron J4125 powered X86 Windows/Linux mini PC, you can set them together with ip cameras for a local AI processed NVR system. Frigate is a completely open source and local NVR designed for Home Assistant with AI-powered object detection. It uses OpenCV and Tensorflow to perform real-time object detection locally for IP cameras. It brings a rich set of features including video recording, re-streaming, motion detection, and supports multiprocessing.
The Coral M.2 Accelerator B+M key integrates an Edge TPU into existing computer systems using an M.2 B-key or M-key interface. This module is particularly well-suited for mobile and embedded systems that can benefit from accelerated machine learning.

Key Features
Performance: The Edge TPU coprocessor is capable of performing 4 trillion operations per second (4 TOPS) with a power consumption of just 2 watts. Modern Mobile Vision models, such as MobileNet v2, can be efficiently run at nearly 400 FPS. Compatibility: Supported on Debian Linux-based systems and Windows 10.
Systems without an M.2 slot can be upgraded using the Coral USB Accelerator.

Technical Specifications
TPU: Google Edge TPU ML accelerator coprocessor (4 TOPS, 2 TOPS per watt) Interface: M.2 B+M-key (via PCIe Gen2 x1 lane) Dimensions: 22 mm x 80 mm x 2.35 mm (M.2-2280-B-M-S3) Weight: 5.8 g Operating Temperature: -20 to +85C

Host System Requirements
Linux: 64-bit Linux Debian 10.0 / Ubuntu 16.04 (or newer), x86-64 or ARMv8 (64-bit) Windows: Windows 10 (64-bit), x86-64 CPU architecture

Important Notes
Refer to the datasheet for peak current requirements (up to 3 A for the Edge TPU) and thermal management. The Edge TPU includes a built-in temperature sensor and allows parameters to be configured for shutdown. Warning: Overheating can lead to fire or hardware damage.

Potential for Industrial Applications

The Coral Edge TPU is a revolutionary product for machine learning applications, enabling embedded solutions that can detect workpiece issues, monitor traffic conditions, and more.

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.