Your position: Home / Development Board

NCSM2852.DK intel Movidius Neural Compute Stick MA2450 Development Board 2450

The Intel Movidius Neural Compute SDK enables rapid phototyping and deployment of deep neural networks (DNNs) on compatible neural compute devices like the Intel Movidius Neural Compute stick. The NCSDK includes a set of software tools to compile, profile
(500 available)
Shipping Cost:
Estimated Delivery Time:
Please select the country you want to ship from
Please select the information you wantX
  • Description
  • Size Chart
  • Measurement
  • Color Chart
  • Reviews
Brand Name: Intel Demo Board Type: MA2450



The Intel® Movidius™ Neural Compute SDK (Intel® Movidius™ NCSDK) enables rapid prototyping and deployment of deep neural networks (DNNs) on compatible neural compute devices like the Intel® Movidius™ Neural Compute Stick. The NCSDK includes a set of software tools to compile, profile, and check (validate) DNNs as well as the Intel® Movidius™ Neural Compute API (Intel® Movidius™ NCAPI) for application development in C/C++ or Python.


The NCSDK has two general usages:

  • Profiling, tuning, and compiling a DNN model on a development computer (host system) with the tools provided in the NCSDK.

  • Prototyping a user application on a development computer (host system), which accesses the neural compute device hardware to accelerate DNN inferences using the NCAPI.

The following diagram shows the typical workflow for development with the NCSDK:


Note that network training phase does not utilize the NCSDK.



        Intel Movidius Neural Compute Stick (NCS) is a tiny fanless deep learning USB drive designed to learn AI programming. The NCS is powered by the low power high performance Movidius Visual Processing Unit (VPU). The VPU can be found in millions of smart security cameras, gesture controlled drones, industrial machine vision equipment, etc. 



  • Supports Convolutional Neural Network (CNN) profiling, prototyping and tuning workflow
  • Real-time on device inference – Cloud connectivity not required
  • Features the Movidius™ Vision Processing Unit (VPU) with energy-efficient CNN processing
  • All data and power provided over a single USB type A port
  • Run multiple devices on the same platform to scale performance



  • Minimum System Requirements:
  • x86_64 computer running Ubuntu 16.04
  • USB 2.0 Type-A port (Recommend USB 3.0)
  • 1GB RAM
  • 4GB free storage space
  • Form Factor: USB Stick
  • Dimensions: 72.5x27x14mm
  • Connectors: USB 3.0 Type A plug
  • Operating Temperature: 0°-40°



  • Smart home and consumer robotics
  • Surveillance and security
  • Retail
  • Healthcare


Intel® Movidius™ Neural Compute Stick

The Intel® Movidius™ Neural Compute Stick (Intel® Movidius™ NCS) enables rapid prototyping of deep neural networks (DNNs) with the Intel® Movidius™ Neural Compute SDK (NCSDK).

o use the NCS, you will need to have the Intel® Movidius™ Neural Compute SDK (Intel® Movidius™ NCSDK) and/or Neural Compute API (NCAPI) installed on your development computer.

Connecting the NCS to a Host Machine

The NCS connects to the host machine over a USB 2.0 High Speed interface. You may plug the NCS directly into a USB port on your host machine or into a USB hub that is plugged into your host machine.


The NCS is powered by the Intel® Movidius™ Myriad™ 2 vision processing unit (VPU).

The VPU includes 4Gbits of LPDDR3 DRAM, imaging and vision accelerators, and an array of 12 VLIW vector processors called SHAVE processors. These processors are used to accelerate neural networks by running parts of the neural networks in parallel.

The NCS is connected to a host machine using the USB interface on the VPU. The USB3 interface can be used both in Super Speed (5 Gbps) or High Speed (480 Mbps) modes.

The VPU also has a SPARC microprocessor core that runs custom firmware. When the NCS is first plugged in, there is no firmware loaded onto it. The VPU boots from the internal ROM and connects to the host machine as a USB 2.0 device. Applications executing on the host machine communicate to the VPU SOC using the Neural Compute API (NCAPI). When the NCAPI initializes and opens a device, the firmware from the Neural Compute SDK (NCSDK) is loaded onto the NCS. At this time, the NCS resets and reconnects to the host machine as either a USB 2.0 or USB 3.0 device (depending on the host type). It is now ready to accept the neural network graph files and instructions to execute inferences.

A graph file is loaded into the DRAM attached to the VPU via the NCAPI. A LEON processor coordinates receiving the graph file and images for inference via the USB connection. It also parses the graph file and schedules kernels to the SHAVE neural compute accelerator engines. In addition, the LEON processor also takes care of monitoring die temperature and throttling processing on high temperature alerts. The output of the neural network and associated statistics are sent back to the host machine via the USB connection and are received by the host application via the NCAPI. 




There is an active user forum for users of the Intel® Movidius™ Neural Compute SDK to discuss ideas and seek troubleshooting help.

Pack list


1x Intel Movidius Neural Compute Stick (NCS)





Movidius Neural Compute SDK Documents:


TensorFlow Support:


Documentation for the NCAPI:


Neural Compute blog:

Expert Support:
Skype: meiqiao_1




Please be aware that due to your computer monitor display the color may have some difference between the picture and the physical item

Please according to you to buy the dress fabric, select the corresponding fabric color chart

Average rating:
Share your thoughts with other customers
Write a review
Product reviews can be carried out after the member login, please click here to login
Message Us