The release of SiMa.ai Palette 1.2 further extends the flexibility and interoperability of SiMa.ai for ML developers as they look to evaluate, prototype, deploy and optimize edge ML applications. Palette 1.2 includes expanded support for C++ and support for installing and developing natively on Windows. This is a large step forward for embedded ML. Whereas Python and Linux are the mainstays of ML development, many traditional machine vision systems are developed using C++ and Windows. Palette 1.2 fosters continued growth of SiMa.ai’s partner ecosystem, specifically in appealing to partners and ISVs who code primarily in C++. With this release, SiMa.ai strengthens its vision of enabling Any Model, Any Pipeline, Any Application at the embedded edge.
Palette 1.2 now supports 200+ models and 7+ calibration schemes/modes. The development team at SiMa continues to add more support for fundamental Palette software functions, including enhancements to Palette Edgematic (50 new models and 9 pipelines have been added to Edgematic.)
SiMa.ai Palette software offers single integration through an innovative, simplified, and automated development flow that focuses on the developer challenges of creating ML applications. GStreamer workflows using advanced scripting and automation tools combine optimized NN Models, pre- and post-processing functions, and applications into a single package for deploying to large numbers of edge devices.
As with prior versions, Palette software continues to provide remote software update capabilities to keep MLSoC systems current with the latest build version. The SiMa.ai developer website also provides a collection of documents that contain user guides, bring-up documentation, API references, and programming guides and examples. Also included are videos demonstrating the installation and configuration of the Palette software as well as the set-up of the developer board. Palette software runs in a Docker container and can be hosted on Windows/Mac/Linux machines. The developer board conveniently runs standalone, or connects via serial port configuration, ethernet, or PCIe for management of the MLSoC and deployed applications.
Current SiMa.ai Palette customers will automatically receive access to Palette 1.2 and prospective customers can apply for access to Palette 1.2 here. Palette 1.2 is also available as part of our DevKit, which can be purchased online here. To learn more about how SiMa.ai can help your organization, for more information or to schedule a demo drop us a line at developer.mlsoc@sima.ai.