Movidius Neural Network Compute Stick

  • RS Stock No. 139-3655
  • Mfr. Part No. NCSM2450.DK1
  • Brand Intel
Technical Reference
Legislation and Compliance
RoHS Certificate of Compliance
COO (Country of Origin): US
Product Details

Movidius Neural Compute Stick

The Neural Network Compute Stick from Movidius™ allows Deep Neural Network development without the need for expensive, power-hungry supercomputer hardware. Simply prototype and tune the Deep Neural Network with the 100Gflops of computing power provided by the Movidius stick. A Cloud connection is not required. The USB stick form-factor makes for easy connection to a host PC while the on-board Myriad-2 Vision Processing Unit (VPU) delivers the necessary computational performance. The Myriad-2 achieves high-efficiency parallel processing courtesy of its twelve Very Long Instruction Word (VLIW) processors. The decision on parallel scheduling is carried out at program compile time, relieving the processors of this chore at run-time.

Features

• Movidius 600MHz Myriad-2 SoC with 12 x 128-bit VLIW SHAVE vector processors • 2MB of 400Gbps transfer-rate on-chip memory
• Supports FP16, FP32 and integer operations with 8-, 16- and 32-bit accuracy
• All data and power provided over a single USB 3.0 port on a host PC
• Real-time, on-device inference without Cloud connectivity
• Quickly deploy existing CNN models or uniquely trained networks
• Multiple Movidius Sticks can be networked to the host PC via a suitable hub
• Dimensions: 72.5 x 27 x 14mm

Compile

Automatically convert a trained Caffe-based Convolutional Neural Network (CNN) into an embedded neural network optimized for the on-board Myriad-2 VPU. The SDK also supports TensorFlow.

Tune

Layer-by-layer performance metrics for both industry-standard and custom-designed neural networks enable effective tuning for optimal real-world performance at ultra-low power. Validation scripts allow developers to compare the accuracy of the optimized model on the device to the original PC-based model.

Accelerate

The Movidius Stick can behave as a discrete neural network accelerator by adding dedicated deep learning inference capabilities to existing computing platforms for improved performance and power efficiency.

Specifications
Attribute Value
Classification Compute Stick
Name Movidius Neural Network Compute Stick
Processor Family Name Myriad
Processor Part Number Myriad-2
Processor Type SoC
428 In stock for FREE next working day delivery
Price Each
£ 69.99
(exc. VAT)
£ 83.99
(inc. VAT)
Units
Per unit
1 - 9
£69.99
10 - 99
£66.91
100 +
£60.85
Related Products
This Intel® Joule™ 570x Developer Kit with Expansion ...
Description:
This Intel® Joule™ 570x Developer Kit with Expansion Board is a development platform for the Intel® Joule™ 570x module.The 570x module is Intel’s high performing compute module and graphics with large memory and multiple high-speed interfaces in a low-power package. By using the expansion board with the Intel® Joule™ 570x ...
The Intel® Joule™ system on module (SoM) are ...
Description:
The Intel® Joule™ system on module (SoM) are Intel’s two high performing compute modules (550x and 570x). Offering options in computing power, graphics, memory and storage in a low-power package. Speed up the development time from prototype to production. Applications areas include: Computer Vision, Mobile Robotics, Drones, Industrial Machine Vision ...
This Intel® Joule™ 550x Developer Kit with Expansion ...
Description:
This Intel® Joule™ 550x Developer Kit with Expansion Board is a development platform for the Intel® Joule™ 550x module. The 550x module is Intel’s high performing compute module and graphics with large memory and multiple high-speed interfaces in a low-power package. By using the expansion board with the Intel® Joule™ ...
The Intel Aero Ready to Fly Drone is ...
Description:
The Intel Aero Ready to Fly Drone is a fully assembled UAV development platform, complete with everything you required to get airborne. The only additional item you need is a fully charged battery. Included on the drone is the Intel RealSense R200 camera, an 8 MP camera and a VGA ...