Machine Learning

OpenNCC NCB

A powerful neural computing board that is a complete, open source replacement for Intel's Neural Compute Stick 2 (NCS2)

This project is launching soon.

Coming Soon
0
updates
You'll be notified about news and stock updates for this project.

OpenNCC NCB is an accelerated AI reference platform designed and manufactured by EyeCloud.AI for edge-ai applications. It is a complete, open source replacement for Intel’s Neural Compute Stick 2 (NCS2). It comes in two variants, a USB version and an FPC version.

The NCB is built with Movidius Myriad X VPU, Intel’s first VPU to feature the Neural Compute Engine - a dedicated hardware accelerator for deep neural network inference. The Neural Compute Engine, in conjunction with the 16 powerful SHAVE cores and high throughput intelligent memory fabric, makes Intel Movidius Myriad X ideal for on-device deep neural networks and computer vision applications. The natively supported Intel® distribution of the OpenVINO™ toolkit automatically maximizes the inference performance.

How OpenNCC NCB replaces the Intel NCS2

OpenNCC NCB functions as the Intel NCS2 with a host machine. The Host App on the Host Machine obtains the video stream (local file, IPC, webcam, or V4L2 Mipi CAM for example) from the outside, configures the preprocessing module according to the resolution and format of the input file of the reasoning model, then sends the visual stream to the OpenNCC NCB through the OpenNCC Native SDK for reasoning and returns the reasoning results. The reasoning supports asynchronous and synchronous modes. The reasoning pipeline on OpenNCC SoM is configured through OpenNCC model JSON.

OpenNCC NCB can support up to a 6-way reasoning pipeline configuration locally, and a 2-way pipeline can run concurrently in real-time. Users can realize multi-level chain or multi-model concurrency of reasoning through intermediate processing of the Host App. OpenNCC NCB can also work with multiples of itself. Users can expand the number of NCB according to their computing power needs, and the SDK will dynamically allocate computing power.

Features & Specifications

Openness

We are happy to provide open hardware board schematics and open software in the form of OpenVINO and OpenNCC Frame.

Interested in This Project?

You can sign up to be notified when this campaign launches, and to get any other useful updates, right at the top of this page. We work hard to only send out useful information and you can unsubscribe at any time.

In the Press

Hackster News

"Using the same Myriad X accelerator, this square open-hardware board aims to accelerate your projects at a low power draw."

About the Team

EyeCloud

San Jose, CA  ·  EyecloudAi  ·  eyecloud.ai

EyeCloud believes in open platform and open source collaboration. We aim to support tech companies overcome development and production challenges of edge AI vision products with expertise in advanced hardware production, embedded software, complex IoT management and cloud services. We also offer engineering services to enable customization to meet application unique requirements.

Johanna Shi

johannasss

Po Yuan

Timotei Redis

TimoteiRedis

See Also

Subscribe to the Crowd Supply newsletter, highlighting the latest creators and projects