IntelNCSM2485.DK-964486 | Neural Compute Stick 2Schnittstellenmodule

AI acceleration device for deep learning development

Intel® Neural Compute Stick 2 | AI Acceleration

The Intel® Neural Compute Stick 2 is a low-cost AI prototyping device for deep learning development with the broad range of frameworks such as Tensorflow, Caffe, and MXNet

- Optimize deep learning models and neural networks for edge devices plugged into a laptop, a single board computer, or any computing platform with a single USB port.

- Compatible with Win10 or Ubuntu 16.04 for wide adoption or developer centric 

- Supports both the latest USB 3.0 and USB 2.0, on any device with a USB port

- Accessible and affordable—take advantage of more performance per watt and highly efficient fanless design in less than 2 watts.

- Combines the hardware-optimized performance of the newest Intel Movidius Myriad X VPU which contains 16 shaves of programmable cores, a dedicated neural compute engine, and optimized internal memory fabric

 

Software

Use with the powerful Intel® Distribution of OpenVINO Toolkit to accelerate deep neural network-based applications which support four Intel architecture of Intel CPUs, Intel GPUs, Intel Movidius VPUs, and Intel FPGAs

- Write your AI deep learning application once, optimize through the Intel® Distribution of OpenVINO Toolkit, prototype on the Intel® NCS 2 and deploy the application to any of the four architectures

- If you are new to learning AI, combine the power of the Intel® NCS 2 with the power of the Intel® Distribution of OpenVINO Toolkit using included pre-trained models or try out models from the Intel Model Zoo available on Github

- Get started quickly with Intel’s developer content and getting started guides or experience some of the reference applications all available at the Intel Developer Zone

Develop applications for retail, manufacturing, safety & security, healthcare, and many other AI use cases. 

A datasheet is only available for this product at this time.