The AI on the PC Development Kit comes with everything you need to develop deep neural network and computer vision applications for the PC. An integration of hardware and software plus source code and tutorials helps accelerate the creation of compelling AI applications and enable new uses.
This kit contains a powerful combination of an Intel® Core™ processor, Intel® Processor Graphics and, for the first time, an Intel® Movidius Myriad™ X Vision Processing Unit (VPU) for high-performance, low-power AI workloads. The three hardware engines run a diverse range of AI workloads to deliver a comprehensive breadth of raw AI capability for mobile PCs.
Hi. I'm Karl Fezer from Intel. In this video, I present an overview of the AI on PC Development Kit. I cover what is included in the kit, show a demo application, and highlight two different AI-powered features. It provides an integrated hardware and software platform for developing PC-based AI solutions.
The goal of the AI on PC Development Kit is to provide a single integrated software and hardware platform for developing PC-based AI solutions. By providing complete support, it eases the development process and allows for exploration of various implementation approaches.
The AI on PC Development Kit hardware is an ASUS* ZenBook Pro Laptop, has an Intel® Core i7 processor, 16 gigabytes of RAM, 512 gigabytes solid state hard drive, and Intel® processor graphics.
A unique feature of the platform is that it includes an internal Intel® Movidius™ Myriad™ X VPU as an M2 card. The AI on PC Development Kit hardware platform allows for the development of AI applications that use the CPU, the integrated GPU, and the VPU.
The kit comes with the following software pre-installed and configured.
The Intel® Distribution of OpenVINO™ toolkit – this is a toolkit for developing deep learning and computer vision applications. Intel® Distribution for Python*– a version of Python* that has been optimized for performance on Intel® architecture. CMake*– a utility for building applications. A 30-day trial of Microsoft Visual Studio* 2019 Enterprise, and all the source code for all of the applications, including what we show in this video.
Also included in the dev kit is Content Illustrating the development of AI solutions using the provided software. For example, OpenVINO-based applications and Windows* ML-based applications. For each environment, there are fully functional code samples, tutorials explaining how to create applications, and Windows Vision Skills, which you can use to add AI capabilities to your applications.
Samples and tutorials are provided for Python, C++, and C# and include native and universal Windows platform applications.
Let's take a closer look at one of the code samples provided with the development kit– the video conferencing application. It has video streaming capabilities for the remote user and uses the camera in real time for the local user.
The sample application allows you to apply AI-based processing to the video streams and select which processor– either the CPU, GPU, or VPU– to use.
Let's use object segmentation to blur out the background of the remote user. Notice we can select which processor to run the inference. Notice that the background of the remote user is now blurred.
Let's try another example– AI video privacy. In this case, the application detects whenever another person enters the video frame, and then blurs the screen. For this demo, we will run the face detection on the CPU and the person detection on the GPU.
Because we are using the GPU, there is a delay. The model has to be loaded onto the GPU, which takes some time. Notice when another person comes into the frame, the video stream is blocked.
The AI on PC Development Kit contains several more examples that you can explore, run, or use to begin your own development. The online user guide provides details on all the available content.
Make sure to check out the links to learn more and to order your AI on PC Development Kit. Thanks for watching.
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.
Notice revision #20110804