> **Source:** Core Electronics is an Australian maker-electronics retailer and manufacturer based in Newcastle, NSW, run by a team of makers and educators. We design and manufacture our own product lines (PiicoDev, CE originals) and are official retailers for iconic maker and industrial brands including Raspberry Pi, Arduino, Adafruit, SparkFun and DFRobot. Orders ship Australia-wide from our Newcastle warehouse. Prices are in AUD and include GST. Pricing, stock and dispatch on this page are generated from the store's live catalog. Full machine-readable index: https://core-electronics.com.au/llms.txt # Coral USB Accelerator **Type:** Product page · **SKU:** SS114991790 · **Brand:** [Seeed Studio](https://core-electronics.com.au/brands/seeed-studio-australia) **Page:** https://core-electronics.com.au/coral-usb-accelerator.html ([markdown](https://core-electronics.com.au/coral-usb-accelerator.html.md)) ## Retired product This product is retired and no longer available for purchase. Replaced by: WS-27812. **Replacement:** https://core-electronics.com.au/catalog/product/view/sku/WS-27812 ## How to buy - **Search the catalogue:** `https://core-electronics.com.au/search/{query}.md` (URL-encode the query; pages 2-3 at `search/{query}/{page}.md`; `search.md?q=` also works) - **Payment methods, purchase orders, policies and contact details:** https://core-electronics.com.au/llms.txt ## Description The Coral USB accelerator brings machine learning inferencing to existing systems. Works with Raspberry Pi and other Linux systems. **Features** - **Performs high-speed ML inferencing:** High-speed TensorFlow Lite inferencing with low power, small footprint, local inferencing - **Supports all major platforms:** Connects via USB 3.0 Type-C to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10 - **Supports TensorFlow Lite:** no need to build models from the ground up. Tensorflow Lite models can be compiled to run on the edge TPE - **Supports [AutoML Vision Edge](https://web.archive.org/web/20230315130625/https://cloud.google.com/vision/automl/docs/edge-quickstart)**: easily build and deploy fast, high-accuracy custom image classification models at the edge. - **Compatible with Google Cloud** The on-board Edge TPU is a small ASIC designed by Google that accelerates TensorFlow Lite models in a power-efficient manner: it's capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power—that's 2 TOPS per watt. For example, one Edge TPU can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 frames per second. This on-device ML processing reduces latency, increases data privacy, and removes the need for a constant internet connection. This allows you to add fast ML inferencing to your embedded AI devices in a power-efficient and privacy-preserving way. Models can be developed in TensorFlow Lite and then compiled to run on the USB Accelerator. **Application** **AI-enabled NVR system** If you are planning to use Coral USB Accelerator for [Home Assistant](https://web.archive.org/web/20230315130625/https://www.home-assistant.io/) of home automation applications, we recommend [Odyssey Blue](https://web.archive.org/web/20230315130625/https://www.seeedstudio.com/Odyssey-Blue-J4125-128GB-p-4921.html), 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. ](https://web.archive.org/web/20230315130625/https://www.seeedstudio.com/Frigate-NVR-with-Odyssey-Blue-and-Coral-USB-Accelerator.html)** [Frigate](https://web.archive.org/web/20230315130625/https://frigate.video/) 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, and motion detection, and supports multiprocessing.** **Object tracking with video**This example takes a camera feed and tracks each uniquely identified object, assigning each object with a persistent ID. The example detection script allows you to specify the tracker program you want to use (the Sort tracker is included). [View on GitHub](https://web.archive.org/web/20230315130625/https://github.com/google-coral/example-object-tracker) **Image recognition with video** Stream images from a camera and run classification or detection models with the TensorFlow Lite API. Each example uses a different camera library, such as GStreamer, OpenCV, PyGame, and PiCamera. [View on GitHub](https://web.archive.org/web/20230315130625/https://github.com/google-coral/examples-camera) **PoseNet pose estimation with video** Use the PoseNet model to detect human poses from images and video, such as locating the position of someone’s elbow, shoulder, or foot.[View on GitHub](https://web.archive.org/web/20230315130625/https://github.com/google-coral/project-posenet) **System requirements** - A computer with one of the following operating systems: - Linux Debian 10, or a derivative thereof (such as Ubuntu 18.04), and system architecture of either x86-64, Armv7 (32-bit), or Armv8 (64-bit) (Raspberry Pi is supported, but Seeed have only tested Raspberry Pi 3 Model B+ and Raspberry Pi 4) - macOS 10.15, with either MacPorts or Homebrew installed - Windows 10 - One available USB port (for the best performance, use a USB 3.0 port) - Python 3.5, 3.6, or 3.7 **Resources** - [**Datasheet**](https://coral.withgoogle.com/tutorials/accelerator-datasheet/) - [**Get started guide**](https://coral.withgoogle.com/tutorials/accelerator/) ## Images - [Product image 1](https://core-electronics.com.au/media/catalog/product/S/S/SS114991790-1.jpg)