Movidius Neural Network Compute Stick

  • RS Stock No. 139-3655
  • Mfr. Part No. NCSM2450.DK
  • Manufacturer Intel
Product overview and Technical data sheets
Legislation and Compliance
RoHS Certificate of Compliance
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
Processor Family Name Myriad
Processor Part Number Myriad-2
Processor Type SoC
537 In stock for delivery within 3 working days
Price Each
HK$ 660.72
(exc. GST)
units
Per unit
1 +
HK$660.72
Related Products
The BISM02BI-01 Module provides a robust and reliable ...
Description:
The BISM02BI-01 Module provides a robust and reliable Bluetooth connection along with a simple AT command based programming interface. Bluetooth 2.0 Class 1 deviceRF Frequency Range: 2.40 to 2.485GHz ISM bandRF Output Power: up to +6d. BmReceiver Sensitivity: -86dBRange: up ...
The RN4871 module is based on the IS187x ...
Description:
The RN4871 module is based on the IS187x Bluetooth device and provides a complete solution to implement Bluetooth 4.2 Low Energy connectivity. The module is interfaced to a host MCU via a UART serial port using Microchip’s ASCII command set ...
The CY5674 PRoC BLE SMA Module enables you ...
Description:
The CY5674 PRoC BLE SMA Module enables you to evaluate and develop Bluetooth Low Energy (BLE) applications with the Programmable System-on-Chip (PSoC) Module. It features an SMA connector for external antenna.The module can be used with the Bluetooth Low Energy ...
The RN4870 module is based on the IS187x ...
Description:
The RN4870 module is based on the IS187x Bluetooth device and provides a complete solution to implement Bluetooth 4.2 Low Energy connectivity. The module is interfaced to a host MCU via a UART serial port using Microchip’s ASCII command set ...