The AI Development Kit contains a powerful combination of an Intel® Core™ processor, integrated graphics from Intel and an Intel® Movidius™ Myriad™ X Vision Processing Unit (VPU) for high performance, low power AI workloads. The three hardware engines are capable of running a diverse range of AI workloads to deliver a comprehensive breadth of raw AI capability for PCs today. This kit includes an Intel® NUC pre-loaded with Windows 10 and AI development tools, code samples and tutorials to help developers fast-track new AI applications.
Intel® Graphics Technology
Intel® Movidius™ Vision Processing Unit (VPU)
Accelerate your deep learning work with this efficient compute solution. Get access to these hardware resources with WinML and the Intel® Deep Learning Deployment Toolkit (available with the Intel Distribution of OpenVINO toolkit) to deliver your AI-enabled products to market.
Available inside many Intel-based PCs, Intel Graphics Technology offers immediate access to powerful acceleration of your most challenging inference workloads. This technology powers WinML and the Intel Distribution of OpenVINO toolkit to deliver efficient GPU acceleration.
This unit enables visual intelligence at a high compute per watt, and supports camera processing, computer vision, and deep learning inference. It is ideal for autonomous service robots, drones, smart IP cameras, digital security and surveillance, smart home, wearables, and more.
Neural Compute Engine: Hardware Based Acceleration for Deep Neural Networks
Myriad™X features the all-new Neural Compute Engine – a purpose-built hardware accelerator designed to dramatically increase performance of deep neural networks without compromising the low power characteristics of the Myriad VPU product line. Featuring an array of MAC blocks and directly interfacing with the intelligent memory fabric, the Neural Compute Engine is able to rapidly perform the calculations necessary for deep inference without hitting the so-called “data wall” bottleneck encountered by other processor designs. Combining the neural network performance of the 16 proprietary SHAVE cores with the neural compute engine, Myriad X delivers 10X the performance compared to previous generations*.
Intel® Bean Canyon NUC
Available with either an Intel® Core™ i5 or i7 processor, dependent upon processing power needs. This unit features 8th Generation NUC hardware and comes with 16GB DDR4 RAM, 256GB or 512GB SSD, Windows 10 Home, and the Intel® Movidius™ Vision Processing Unit (VPU). Everything is pre-installed, tested, and ready to go to provide developers an out-of-the-box AI development solution.
- Dedicated Neural Compute Engine
- 16 High Performance SHAVE Cores
- Enhanced ISP with 4K support
- New Vision Accelerators including Stereo Depth
- Native FP16 and fixed point 8 bit support
- Rapidly port and deploy neural networks in Caffe and Tensorflow formats
- End-to-End acceleration for many common deep neural networks
- Industry-leading Inferences/S/Watt performance
While the AI Dev Kit is capable of performing computation on images from the internet or images saved to a local hard drive, get the most out of the Movidius Vision Processing Unit by pairing your solution with a camera.
We offer the kit with either a Logitech C525 720p camera or Logitech C920 1080p camera, depending on the resolution needs of incoming images with your AI development.
Windows Machine Learning* (WinML)
Intel® Distribution of OpenVINO™ Toolkit
The toolkit is targeted at developers who need hardware customization options and support for multiple operating systems. Accelerate development of high-performance computer vision and deep learning inference into vision applications. Enable deep learning on hardware accelerators and flexible deployment across multiple types of Intel® platforms (CPU, GPU with Intel® Processor Graphics, and VPU). This distribution includes the Intel® Deep Learning Deployment Toolkit with a model optimizer and inference engine.