Coral USB Accelerator

GoogleSKU: 102990
(10 Reviews)
Sale price £80
incl. VAT
excl. VAT
Sold out
Notify me

Compatible with:

Awesome Extras

(2475 Reviews)
Raspberry PiRaspberry Pi 4 Model B
Sale priceFrom £40incl. VAT excl. VAT
(2436 Reviews)
The Pi HutRaspberry Pi 4 Model B Starter Kit
Sale priceFrom £69 incl. VAT excl. VAT
(2 Reviews)
The Pi HutUSB-C Extension Cable for Raspberry Pi 4
Sale price £6 incl. VAT excl. VAT

The Coral USB Accelerator is a USB accessory that brings machine learning inferencing to existing systems. It works with the Raspberry Pi and Linux, Mac, and Windows systems.

The Accelerator adds an Edge TPU coprocessor to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port!

Performs High-speed Machine Learning 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 almost 400 FPS, in a power-efficient manner. See below section for performance benchmarks.

Supports 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 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.

Tech specs

ML accelerator Google Edge TPU coprocessor:
4 TOPS (int8); 2 TOPS per watt
Connector USB 3.0 Type-C* (data/power)
Dimensions 65 mm x 30 mm

* Compatible with USB 2.0 but inferencing speed is much slower.

Datasheet & Resources

Performance Benchmarks

An individual Edge TPU is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). How that translates to performance for your application depends on a variety of factors. Every neural network model has different demands, and if you're using the USB Accelerator device, total performance also varies based on the host CPU, USB speed, and other system resources.

With that said, the table below compares the time spent to perform a single inference with several popular models on the Edge TPU. For the sake of comparison, all models running on both CPU and Edge TPU are the TensorFlow Lite versions.

This represents a small selection of model architectures that are compatible with the Edge TPU:

Note: These figures measure the time required to execute the model only. It does not include the time to process input data (such as down-scaling images to fit the input tensor), which can vary between systems and applications. These tests are also performed using C++ benchmark tests, whereas our public Python benchmark scripts may be slower due to overhead from Python.

Model architecture Desktop CPU 1 Desktop CPU 1
+ USB Accelerator (USB 3.0)

with Edge TPU
Embedded CPU 2 Dev Board 3
with Edge TPU
Unet Mv2
27.7 3.3 190.7 5.7
DeepLab V3
394 52 1139 241
380 20 1032 25
Inception v1
90 3.4 392 4.1
Inception v4
700 85 3157 102
Inception-ResNet V2
753 57 2852 69
MobileNet v1
53 2.4 164 2.4
MobileNet v2
51 2.6 122 2.6
MobileNet v1 SSD
109 6.5 353 11
MobileNet v2 SSD
106 7.2 282 14
ResNet-50 V1
484 49 1763 56
ResNet-50 V2
557 50 1875 59
ResNet-152 V2
1823 128 5499 151
55 2.1 232 2
867 296 4595 343
1060 308 5538 357
EfficientNet-EdgeTpu-S* 5431 5.1 705 5.5
EfficientNet-EdgeTpu-M* 8469 8.7 1081 10.6
EfficientNet-EdgeTpu-L* 22258 25.3 2717 30.5

1 Desktop CPU: Single 64-bit Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
2 Embedded CPU: Quad-core Cortex-A53 @ 1.5GHz
3 Dev Board: Quad-core Cortex-A53 @ 1.5GHz + Edge TPU

Payment & Accreditations

Payment methods
Amazon American Express Maestro Mastercard PayPal Visa

Your payment information is processed securely. We do not store credit card details nor have access to your credit card information.