Coral USB Accelerator

GoogleSKU: 102990
(31 Reviews)
Price:
Sale price £62
incl. VAT
excl. VAT
Stock:
Sold out
Notify me

Compatible with:

Awesome Extras

Raspberry Pi 4 Model B by Raspberry Pi - The Pi HutRaspberry Pi 4 Model B by Raspberry Pi - The Pi Hut
(3218 Reviews)
Raspberry PiRaspberry Pi 4 Model B
Sale priceFrom £33.30 incl. VAT excl. VAT
Raspberry Pi 4 Model B Starter Kit by The Pi Hut - The Pi HutRaspberry Pi 4 Model B Starter Kit by The Pi Hut - The Pi Hut
(2762 Reviews)
The Pi HutRaspberry Pi 4 Model B Starter Kit
Sale priceFrom £60 incl. VAT excl. VAT
USB-C Extension Cable for Raspberry Pi 4 by The Pi Hut - The Pi HutUSB-C Extension Cable for Raspberry Pi 4 by The Pi Hut - The Pi Hut
(9 Reviews)
The Pi HutUSB-C Extension Cable for Raspberry Pi 4
Sale price £6 incl. VAT excl. VAT
Raspberry Pi USB 3 Hub by Raspberry Pi - The Pi HutRaspberry Pi USB 3 Hub by Raspberry Pi - The Pi Hut
(17 Reviews)
Raspberry PiRaspberry Pi USB 3 Hub
Sale price £11.20 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
(128x128)
27.7 3.3 190.7 5.7
DeepLab V3
(513x513)
394 52 1139 241
DenseNet
(224x224)
380 20 1032 25
Inception v1
(224x224)
90 3.4 392 4.1
Inception v4
(299x299)
700 85 3157 102
Inception-ResNet V2
(299x299)
753 57 2852 69
MobileNet v1
(224x224)
53 2.4 164 2.4
MobileNet v2
(224x224)
51 2.6 122 2.6
MobileNet v1 SSD
(224x224)
109 6.5 353 11
MobileNet v2 SSD
(224x224)
106 7.2 282 14
ResNet-50 V1
(299x299)
484 49 1763 56
ResNet-50 V2
(299x299)
557 50 1875 59
ResNet-152 V2
(299x299)
1823 128 5499 151
SqueezeNet
(224x224)
55 2.1 232 2
VGG16
(224x224)
867 296 4595 343
VGG19
(224x224)
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
Visa Mastercard Maestro PayPal Amazon Klarna

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

Accreditations
Based on 31 reviews
Write Review
Review Image - Coral USB Accelerator
Rob S
Review Image - Coral USB Accelerator
Evgeniy B
Clear Filters
Order By
Newest First
Oldest First
Most Popular
Highest Rating
Breakdown
27
2
1
0
1
Verified Customer
Anonymous
Coral USB Accelerator
WARNING: Extremely difficult to set up. Even on standard Linux distributions like Ubuntu, you really need to check kernel module drivers support, their versions, and if you need to compile the driver from source, etc. It is far away from being plug and play. There's only one way to make it work in macOS, and it is by using QEMU.
Was this review helpful?
Yes
Report
Share
3 months ago
Verified Customer
Helen W
Rochester, United Kingdom
Coral USB Accelerator
setting up was interesting but once done love it
1 person found this review helpful.
Was this review helpful?
Yes
Report
Share
5 months ago
Verified Customer
Anonymous
Coral USB Accelerator
I bought this for Frigate in Home Assistant on my RPi5 with 5 cameras, and I have to say it now copes very well with object detection, reducing my main CPU usage massively as well as the system memory. I would definitely recommend this.
Review Image - Coral USB Accelerator
3 people found this review helpful.
Was this review helpful?
Yes
Report
Share
6 months ago
Verified Customer
Ben S
Manchester, United Kingdom
Coral USB Accelerator
I bought this to be the brains in my Frigate cctv Pi, worked better than expected, 2 4k cameras from crashing the system constantly to instant notifications when a person is spotted.
2 people found this review helpful.
Was this review helpful?
Yes
Report
Share
1 year ago
Verified Customer
Tom M
Martinez, United States
Coral USB Accelerator
These require a lot of work but there is nothing like it. Do some homework and it will be clear why these are cool and you will know if it is for you.
Was this review helpful?
Yes
Report
Share
2 years ago
Verified Customer
John B
Coral USB Accelerator
Working perfectly well after ensuring plugged into a USB3 instead of USB2 port. Since then working flawlessly to provide efficient object detention as part of a Frigate setup for home CCTV for past week.
4 people found this review helpful.
Was this review helpful?
Yes
Report
Share
2 years ago
Verified Customer
Nicolo P
Coral USB Accelerator
Great. It allows to test AI algorithm with a regular pc
Was this review helpful?
Yes
Report
Share
2 years ago
Verified Customer
Anonymous
Loughborough, United Kingdom
Coral USB Accelerator
Reviewer didn't leave any comments
Was this review helpful?
Yes
Report
Share
2 years ago
1
2
3
4

New content loaded