OpenNCC NCB is an accelerated-AI reference platform designed and manufactured by EyeCloud for edge-AI applications. It is a complete, open-source replacement for Intel’s Neural Compute Stick 2 (NCS2).
OpenNCC Neural Compute Board (NCB) is built with Intel’s Movidius Myriad X VPU, the same chip used in the NCS. It’s Intel’s first VPU to feature the Neural Compute Engine (NCE), a dedicated hardware accelerator for deep neural-network inference. This NCE, in conjunction with 16 powerful SHAVE cores and high-throughput intelligent memory fabric, makes Movidius Myriad X ideal for on-device deep neural networks and computer-vision applications.
This NCB also provides native support for the Intel® distribution of the OpenVINO™ Toolkit, which automatically maximizes its inference performance. Developers can quickly and easily switch to different OpenVINO versions by installing different revisions of the firmware. (As of now, it supports OpenVINO 2020.3 and 2021.4.)
You can also use OpenNCC NCB with GStreamer by replacing the local firmware with OpenNCC Frame. Used in this way, the NCB functions as an Intel NCS2 with a host machine. The Host App on the Host Machine obtains the video stream (from a local file, IPC, webcam, or V4L2 MIPI cam, for example), configures the pre-processing 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 and returns the reasoning results. It supports both synchronous and asynchronous reasoning modes, and you can configure the reasoning pipeline on the OpenNCC SoM using an OpenNCC JSON model.
This NCB supports up to a 6-way reasoning pipeline, locally, and a 2-way pipeline can run concurrently in realtime. You can realize multi-level chain or multi-model reasoning concurrency through intermediate processing via the Host App. You can also connect multiple OpenNCC NCBs together, and the SDK will dynamically allocate computing power to accommodate your needs as they fluctuate.
While Intel’s NCS was optimized for rapid prototyping, OpenNCC NCB is equally well suited to mass production. All commercial edge-AI projects face a challenge when it comes time to scale up from the development phase. Design optimizations are only part of the solution, especially for teams that lack extensive manufacturing experience. As a result, we also provide ODM/OEM services to help OpenNCC-NCB-based projects advance from prototyping to DVT, through PVT, and all the way to mass production.
OpenNCC NCB supports the TensorFlow, Caffe, Apache MXNet, and Open Neural Network Exchange (ONNX) frameworks, as well as the PaddlePaddle framework by way of an ONNX conversion. Furthermore, its compatibility with Intel’s distribution of the OpenVINO Toolkit means you can easily deploy pre-trained models from the Open Model Zoo.
|OpenNCC NCB||Intel NCS2||megaAI|
|Processor||Intel Movidius Myriad X VPU||Intel Movidius Myriad X VPU||Intel Movidius Myriad X VPU|
|Material & Design||PCBA||Metal USB stick||PCBA|
|Connectivity||USB 2.0/3.0 Type-C with a C-A cable||USB 3.1 Type-A, USB 2.0 Type-A||USB 3 Type-C 3.1 Gen1|
|Image Data Source||Video streaming from external cameras or in-stock images||Video streaming from external cameras or in-stock images||On-board camera|
|Dimensions||1.50 x 1.50 in (38 x 38 mm)||2.85 x 1.06 x 0.55 in (72.5 x 27 x 14 mm)||1.77 in x 1.18 in (45 mm x 30 mm)|
|Weight||0.32 oz (9 g)||1.24 oz (35.2 g)||2 oz (57.7 g) with enclosure|
|Open Source||HW and SW||SW only||HW and SW|
|Design Usage||Good for tiny products or large systems||Good for large systems||Good for tiny products or large systems|
|R&D Stage Fit||Good for all stages from prototyping to mass production||Good for prototyping||Good for all stages from prototyping to mass production|
|Availability||Crowdfunding||End of life||In stock|
|Commercial ODM Service||Available||Not available||Available|
|Commercial OEM Service||Available||Not available||Unknown|
|Price||$126||No longer sold||$199|
We are happy to provide getting-started guides, open-hardware design documents, and open-source software in the form of OpenVINO and OpenNCC Frame. We have a support forum as well, and you can reach out using the appropriate link below if you have a question.
Our first batch will consist of 200 units, which will ship out to backers according to when they placed their order. Remaining orders will be covered by a second manufacturing run and will ship out to backers approximately three months after the first batch.
We will ship the first batch of 200 units to Crowd Supply’s warehouse within four months of the campaign’s end. These units should go out to backers approximately one month after that. The second batch, which should cover all remaining orders, will ship approximately three months later. Mouser Electronics will distribute all OpenNCC NCB products to backers worldwide. You can learn more about Crowd Supply’s fulfillment service under Ordering, Paying, and Shipping in their guide.
We and our prototype reviewers have tested and verified both OpenNCC NCB boards, which worked as expected. Our manufacturing supply chain has also been tested, as we have successfully produced 200 units. Nonetheless, any manufacturing process is subject to delays caused by unexpected lead-time extensions. We are doing our best to prevent this, and will keep our subscribes posted through regular campaign updates, both during and after the campaign.
"Using the same Myriad X accelerator, this square open-hardware board aims to accelerate your projects at a low power draw."
"The accelerated AI reference platform will support on-board inference AI models and work well with Raspberry Pi boards as well as other Arm Linux SoCs."
"Compatible con una solución de una gran fabricante, la nueva placa de computación neuronal OpenNCC NCB ofrece un alto rendimiento siguiendo el paradigma del software libre."
Produced by EyeCloud in San Jose, CA.
Sold and shipped by Crowd Supply.
One OpenNCC Neural Compute Board (NCB) with a USB Connector. Works much like the Intel Neural Computer Stick 2 (NCS2). USB Type-C to Type-A cable not included. Please use with a USB Type-C 3.1 or 3.2 Gen 2 cable with support for 10 Gbps data transfer.
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.
A stackable, high-performance, Rockchip RK3588 single board computer in a Pico-ITX form factor
An embedded platform for combining Depth and AI, built around Myriad X
A high-performance SDR seamlessly integrated with state-of-the-art deep learning hardware