Intel Movidius Neural Network Compute Stick Deep Neural Network USB Stick with Myriad-2 - NCSM2450.DK1

  • RS-lagernummer 139-3655
  • Producentens varenummer NCSM2450.DK1
  • Produsent Intel
Tekniske datablader
Regulativer og opprinnelsesland
RoHS-Deklarasjon
COO (Country of Origin): CN
Produktdetaljer

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.
Where can you use me?
• Smart home and consumer robotics
• Surveillance and security industry
• Retail industry
• Healthcare

Spesifikasjoner
Attribute Value
Classification Development Tool
Kit Name Movidius Neural Network Compute Stick
Technology Deep Neural Network
Processor Family Name Myriad
Processor Part Number Myriad-2
Processor Type SoC
999 Innen 1 virkedag(er) (UK-lager)
Pris ekskl. MVA Each
kr 789,81
(ekskl. MVA)
kr 987,26
(inkl. MVA)
enheter
Per unit
1 - 9
kr 789,81
10 - 99
kr 724,89
100 +
kr 661,46
Relaterte Produkter
The Atmel ZigBit™ USB Stick ATZB-X-233-USB supports the ...
Description:
The Atmel ZigBit™ USB Stick ATZB-X-233-USB supports the AT86RF233 + ATxmega256A3U MCU wireless module. It is used to evaluate the module while plugged into a USB socket on a PC. The ZigBit module is compatible with a ZigBee stack that ...
The Blackfin media player starter kit provides you ...
Description:
The Blackfin media player starter kit provides you everything you need to get started on a media player application using a Blackfin EZ-KIT Lite and included software to perform audio and graphic related tasks. Learn how to render audio contents ...
The Innodisk USB Drive products provide high capacity ...
Description:
The Innodisk USB Drive products provide high capacity USB flash memory storage that electrically complies with High-speed USB 2.0 interface and backward compatible with USB 1.1. The device features attractive small form factor and the connectivity over USB2.0 and the ...
Transcend's USB Flash modules are convenient, easy to ...
Description:
Transcend's USB Flash modules are convenient, easy to implement solutions for expanding the memory capacity of industrial computers. These compact storage devices consume a minimal amount of power and feature a mechanical write protection switch. Due to their minimalist dimensions, ...