PRODUCT BRIEF
Intel® Neural Compute Stick 2
High performance, Low Power
for AI Inference
Introduction
Bringing computer vision and AI to your IoT and edge device
prototypes are now easier than ever with enhanced
capabilities of the Intel® Neural Compute Stick 2 (Intel® NCS2).
Learn more about
Intel® Neural
Compute Stick 2 at
http://intel.com/ncs
Whether you’re developing a smart camera, a drone with
gesture-recognition capabilities, an industrial robot, or the next,
must-have smart home device, the Intel® NCS2 offers what you
need to prototype smarter.
What looks like a standard USB thumb drive hides much more
inside. It’s built on the latest Intel® Movidius™ Myriad™ X VPU
which features the neural compute engine—a dedicated
hardware accelerator for deep neural network inferences. With
more compute cores than the original version and access to the
Intel® Distribution of OpenVINO™ toolkit, the Intel® NCS2
delivers 8X* performance boost over the previous generation.
Product features
• Powered by Intel® Movidius™ Myriad™ X Vision Processing Unit
• Up to 8X* the performance of Intel® Movidius™ Neural Compute Stick
• Supported by the Intel® Distribution of OpenVINO™ toolkit
• Real-time, on device inference - cloud connectivity not required
• Run multiple devices on the same platform to scale performance
1
Where to buy
Purchase your Intel® Neural Compute Stick 2 from one of our trusted partners at: Where to Buy
Intel® Neural Compute Stick 2 | Product Sheet
Vision Processing Unit Architecture
Neural Compute Engine
16 SHAVE
Programmable Cores
Intel® Movidius™ Myriad™ X VPU
VLIW (DSP)
An entirely new
deep neural
network (DNN)
inferencing engine
that offers flexible
interconnect and
ease of configuration
for on-device DNNs
and computer
vision applications
Interfaces
LPDDR
programmable
processors are
optimized for
complex visions and
imaging workloads
Homogeneous
memory design for
low-power, UL
latency, sustained
High Performance
Intel® Distribution of OpenVINO™ toolkit
The Intel Distribution of OpenVINO™ toolkit is the default software development kit¹ to optimize performance, integrate deep learning inference, and run deep neural networks (DNN)
on Intel® Movidius™ Vision Processing Units (VPU).
Download Open Source GitHub Repo
Deep Learning Computer Vision
OpenCV, OpenCL™,
OpenVX
Caffe*, Tensorflow*, mxnet*,
ONNX*, PyTorch*, PaddlePaddle*
Pretrained models
The Intel® Distribution of OpenVINO™ toolkit includes two
sets of optimized models that can expedite development
and improve image processing pipelines for Intel® processors. Use these models for development and production
deployment without the need to search for or to train your
own models.
Full list of models at: Pretrained Models
Reference Implementations
Open-sourced reference implementations to quickly deploy with pre-built projects
Intruder Detector
Build an application that alerts you when someone
enters a restricted area. Learn how to use models for
multiclass object detection.
Restricted Zone Notifier
Secure work areas and send alerts if someone enters
the restricted space.
Store Traffic Monitor
Monitor three different streams of video that count
people inside and outside of a facility. This application
also counts product inventory.
Shopper Gaze Monitor
Build a solution to analyze customer expressions and
reactions to product advertising collateral that is
positioned on retail shelves.
Parking Lot Tracker
Receive or post information on available parking
spaces by tracking how many vehicles enter and exit a
parking lot.
Machine Operator Monitor
Send notifications when an employee appears to be
distracted when operating machinery.
View all reference implementations
Intel® Neural Compute Stick 2 | Product Sheet
Projects
AI has the power to save lives, protect the environment, and change the world. Start your AI at
the edge development today.
Smart Shopping Cart
Gives off-line retailers additional
opportunities to advertise products in a
fashion similar to online sellers (i.e., Based
on the products already placed in a
shopping cart)
3D Printing Error Detection
Offline analysis is accomplished with a
Machine Learning and Mammography
Detecting invasive ductal carcinoma with
convolutional neural networks showing how
existing deep learning technologies can be
utilized to train artificial intelligence (AI) to be
able to detect invasive ductal carcinoma (IDC)
1 (breast cancer) in unlabeled histology
images.
digital microscope connected to a laptop
running Ubuntu* and the Intel® Neural
Compute Stick 2. After analysis,
contamination sites are marked on a map
in real time.
CORaiL: Coral Reef Restoration and Research
Prototype a fully functional modular
AI-powered underwater camera unit that
continuously counts the number of visible
fauna, and, as possible, assign a taxonomy.
Technical Specifications
Specifications
Intel® Neural Compute Stick 2
Vision Processing Unit (VPU) The Intel® Movidius™ Myriad™ X VPU
Software development kit
Operating Systems support
Intel® Distribution of OpenVINO™ toolkit
Ubuntu* 16.04.3 LTS (64 bit), Windows® 10 (64
bit), CentOS* 7.4 (64 bit), Raspbian*, and other via
the open-source distribution of OpenVINO™
toolkit
Supported framework
TensorFlow*, Caffe*, MXNet*, ONNX*, and
PyTorch* / PaddlePaddle* via ONNX* conversion
Connectivity USB 3.1 Type-A, USB 2.0 Type-A
Dimensions 72.5mm X 27mm X 14mm
Operating temperature 0° - 40° C
Material Master Number
MSRP
Supported platforms
964486
$69 USD
as of July 14, 2019
x86_64, ARM
Additional Resources
• Getting Started
• Forum
• Tutorials
1
Testing by Intel as of October 12th, 2018
Deep Learning Workload Configuration. Comparing Intel® Movidius™ Neural Compute Stick based on Intel® Movidius™ Myriad™ 2 VPU vs. Intel® Neural
Compute Stick 2 Intel® Movidius™ Myriad™ X VPU with Asynchronous Plug-in enabled for (2xNCE engines). As measured by images per second across
GoogleNetV1. Base System Configuration: Intel® Core™ I7-8700K 95W TDP (6C12T at 3.7GHz base freq and 4.7GHz max turbo freq), Graphics: Intel®
UHD Graphics 630 Total Memory 65830088 kB Storage: INTEL SSDSC2BB24 (240GB), Ubuntu 16.04.5 Linux-4.15.0-36-generic-x86_64-with-Ubuntu-16.04-xenial, deeplearning_deploymenttoolkit_2018.0.14348.0, API version 1.2, Build 14348, myriadPlugin, FP16, Batch Size = 1. Software and
workloads used in performance tests may have been optimized for performance only on Intel® microprocessors. Performance tests, such as SYSmark
and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors
may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated
purchases, including the performance of that product when combined with other products. For more complete information visit www.intel.com/bench-
marks. Performance results are based on testing as of October 12th, 2018 and may not reflect all publicly available security updates. See
configuration disclosure for details. No product can be absolutely secure.
Copyright © 2019 Intel Corporation. All rights reserved. Intel, the Intel Logo, Movidius, and OpenVINO are trademarks of Intel Corporation or its
subsidiaries in the U.S. and/or other
countries.
*Other names and brands may be claimed as the property of others.
Loading...