Toybrick RK1808 AI USB Compute Stick for Deep Learning, up to 3 TOPs powered by Rockchip NPU
Quantity Discounts:
- 5-10 $213.77 (exc GST)
- 10+ $207.09 (exc GST)
Out of Stock
Sign up to get notified when it's available to order.
Description
Toybrick RK1808 AI USB Compute Stick is a high-performance and low-power consumption USB accelerator designed for Deep Learning. It is equipped with Rockchip RK1808 Neural Processing Unit (NPU) features an accelerator delivering up to 3.0 TOPS and is coupled with two low-power Arm Cortex-A35 cores allowing it to run Linux. RK1808 AI USB computing stick can be used for AI inference, and also supports custom development for any specific AI application. How is the performance? So that’s roughly equivalent to the Intel® Movidius™ Myriad™ X said 4 TOPs. The stick also comes with 1GB of LPDDR memory, and onboard 8GB of EMMC storage when you connect to a host computer.
Features
- Powerful AI computing power: built-in RK1808 NPU up to 3 TOPS, dual-core Cortex-A35 architecture.
- Strong compatibility: host server supports Windows, Linux, macOS, and Arm Linux.
- Prepare for AI developers: RKNN toolkit offers development support in both C++ and Python. Model conversion supports mainstream frameworks including PyTorch, TensorFlow,Caffe, MXNet
- Scalability: supports multiple stick overlays on the same platform to increase host performance.
- Built-in storage, use as a USB disk with the documentation and software tools stored on the stick itself.
Work as an AI accelerator
You’ll need to install the RK1808 compute stick on another Ubuntu 16.04/x86_64 PC if you want to convert your models to use on the Arm device like Raspberry Pi.
RKNN-Toolkit is an SDK for model conversion, inference, and performance evaluation
The host computer transmits the model and pre-processed data to the RK1808 artificial intelligence computing stick through RKNN-Toolkit, and the RK1808 artificial intelligence computing stick completes the inference and returns the results to the host computer, and the host computer performs post-processing and display operations.
The following platforms and systems are supported as host machines:
- At least Ubuntu 16.04/x86_64 PC or higher, Windows, Mac OS
- RK3399, RK3399Pro, Android system
The overall data flow diagram is as follows:
Connecting the RK1808 USB Stick to a Host Computer
The rknn-toolkit is already installed inside the RK1808 AI computing stick by default. The host computer does not need to install rknn-toolkit and rknn-api. The host computer only needs to connect to the computing stick through the USB port. Input data (such as images and video streams), the RK1808 artificial intelligence computing stick automatically completes the pre-processing, inference, and post-processing of the data, and then outputs the processing results to the host computer through the USB port.
The host computer here can be any platform with a USB interface and any operating system, including X86/X64/Arm32/Arm64, Linux/Windows/Mac OS and Raspberry Pi, etc…
Specifications
| CPU | RK1808 |
| Memory | 1GB LPDDR |
| Storage | 8GB EMMC |
| Size | 82×31×13mm |
| Interface | USB3.0 Type-A |
| Mini-system requirement | Ubuntu 16.04 or x86_64 PCCPU intel core i3USB 3.02 GB RAM4 GB Storage |
| Temperature | 0°C ~ 40°C |
Documentations
Exact shipping can be calculated on the view cart page (no login required).
Products that weigh more than 0.5 KG may cost more than what's shown (for example, test equipment, machines, >500mL liquids, etc).
We deliver Australia-wide with these options (depends on the final destination - you can get a quote on the view cart page):
- $3+ for Stamped Mail (typically 10+ business days, not tracked, only available on selected small items)
- $6+ for Standard Post (typically 6+ business days, tracked)
- $10+ for Express Post (typically 2+ business days, tracked)
- Pickup - Free! Only available to customers who live in the Newcastle region (must order online and only pickup after we email to notify you the order is ready). Orders placed after 2PM may not be ready until the following business day.
Non-metro addresses in WA, NT, SA & TAS can take 2+ days in addition to the above information.
Some batteries (such as LiPo) can't be shipped by Air. During checkout, Express Post and International Methods will not be an option if you have that type of battery in your shopping cart.
International Orders - the following rates are for New Zealand and will vary for other countries:
- $11+ for Pack and Track (3+ days, tracked)
- $16+ for Express International (2-5 days, tracked)
If you order lots of gear, the postage amount will increase based on the weight of your order.
Our physical address (here's a PDF which includes other key business details):
Unit 18, 132 Garden Grove Parade
Adamstown
NSW, 2289
Australia
Take a look at our customer service page if you have other questions such as "do we do purchase orders" (yes!) or "are prices GST inclusive" (yes they are!). We're here to help - get in touch with us to talk shop.
Have a product question? We're here to help!
Solderless Breadboard - 400 Tie Points (ZY-60)SKU: CE05102 Brand: Core ElectronicsPerfect for prototyping.- Solderless Breadboard - 3220 Tie Point (ZY-208)SKU: CE05315 Brand: Core ElectronicsThis is our largest solderless breadboard. Ideal for those large projects or jus ...
- Bus Pirate CableSKU: CAB-09556 Brand: SparkfunThis is an interface cable for the Bus Pirate v3/v3.6, designed to connect to th ...
- Bus Pirate - v3.6aSKU: TOL-12942 Brand: SparkfunThe Bus Pirate v3.6a, created by Ian Lesnet, is a troubleshooting tool that comm ...
Videos
View AllGuides
Integrated Computer Vision Package - OAK-D Lite With Raspberry Pi Set Up
Pose Estimation and Face Landmark Tracking with Raspberry Pi and OpenCV
Hand Recognition and Finger Identification with Raspberry Pi and OpenCV
Face and Movement Tracking Pan-Tilt System with Raspberry Pi and OpenCV
Projects
Analogue Quad Oscillator Drone Synth
Raspberry Pi Microscope
Accurate IoT Clock With ESP8266
Makers love reviews as much as you do, please follow this link to review the products you have purchased.
Product Comments