Intel® Neural Compute Stick 2 (Intel® NCS2)
A Plug and Play Development Kit for AI Inferencing
- Build and scale with exceptional performance per watt per dollar on the Intel® Movidius™ Myriad™ X Vision Processing Unit (VPU)
- Start developing quickly on Windows® 10, Ubuntu*, or macOS*
- Develop on common frameworks and out-of-the-box sample applications
- Operate without cloud compute dependence
- Prototype with low-cost edge devices such as Raspberry Pi* 3 and other ARM* host devices
Previous Version: Intel® Movidius™ Neural Compute Stick (NCS)
Intel® Distribution of OpenVINO™ Toolkit
Intel NCS2
Develop, fine-tune, and deploy convolutional neural networks (CNNs) on low-power applications that require real-time inferencing.
- Deep learning inference at the edge
- Pretrained models on Open Model Zoo
- A library of functions and preoptimized kernels for faster delivery to market
- Support for heterogeneous execution across computer vision accelerators—CPU, GPU, VPU, and FPGA—using a common API
- Raspberry Pi hardware support
New Features
Explore the latest features and release notes for the toolkit.
- Includes Deep Learning Workbench
- Supports multidevice inference for load balancing
- Offers binary distribution methods via package managers and Docker* containers
- Provides new inference engine centric APIs
- Supports serialized FP16 Intermediate Representation
- Explore use cases for machine translation, natural language processing, and more
Technical Specifications
Hardware
- Processor: Intel Movidius Myriad X Vision Processing Unit (VPU)
- Supported frameworks: TensorFlow*, Caffe*, Apache MXNet*, Open Neural Network Exchange (ONNX*), PyTorch*, and PaddlePaddle* via an ONNX conversion
- Connectivity: USB 3.0 Type-A
- Dimensions: 2.85 in. x 1.06 in. x 0.55 in. (72.5 mm x 27 mm x 14 mm)
- Operating temperature: 0° C to 40° C
Software
- Intel Distribution of OpenVINO toolkit
- Supported operating systems:
- Ubuntu 16.04.3 LTS (64 bit)
- CentOS* 7.4 (64 bit)
- Windows 10 (64 bit)
- macOS 10.14.4 (or later)
- Raspbian (target only)
- Other (via the open source distribution of OpenVINO™ toolkit)
Intel® Movidius™ Myriad™ X Vision Processing Unit (VPU)
The latest generation of Intel® VPUs includes 16 powerful processing cores (called SHAVE cores) and a dedicated deep neural network hardware accelerator for high-performance vision and AI inference applications—all at low power.
Plug-and-Play AI
Prototype with low-cost edge devices, such as Raspberry Pi* and other Arm* host devices.
Build cutting-edge AI and machine learning into your PC applications with the Intel® NUC.
Depth sensing meets plug-and-play edge inferencing with AI using an Intel® RealSense™ Depth Camera D400 series.
Reference Implementations
Learn to build computer vision solutions on the Intel® NCS2 by developing these projects.
Warranty Support & Regulatory Information
Consult the Intel Neural Compute Stick 2 support for initial troubleshooting steps. If the issue persists, follow these instructions to obtain warranty support:
- For purchases made from a distributor less than 30 days from the time of the warranty support request, contact the distributor where you made the purchase.
- For purchases made directly from Intel or from a distributor more than 30 days from the time of the warranty support request, contact Intel Warranty Support. Note You will need to create a support account if you do not have one.