SiMa.ai, the machine learnin
Palette Edgematic enables a “drag and drop,” code-free approach where users can create, build and deploy their own models and complete computer vision pipelines automatically in minutes versus months, while evaluating the performance and power consumption needs of their edge ML application in real time. ML applications evaluated and developed with Palette Edgematic can later be deployed and executed on a SiMa Developer or Production board.
With the release of Palette Edgematic, SiMa.ai is pioneering a new normal in ease of use for edge AI and ML. In parallel, SiMa.ai continues to raise the bar in setting a new performance standard for ML at the embedded edge, having earlier announced this week a new milestone in FPS/W excellence in the most recent ML Perf 3.1 benchmark competition.
With Palette Edgematic, anyone with a computer vision pipeline concept can evaluate it directly on an edge device without an intermediate step in the cloud, providing a direct path to implementation at the edge. With Palette Edgematic, a developer can:
-
Rapidly prototype and evaluate ML pipelines on edge devices in minutes;
-
Use real-time data streams to measure KPIs and then use the Palette Edgematic new visual canvas to rapidly iterate design to improve pipeline performance, eliminating the specialized embedded coding translation for edge ML implementations;
-
Utilize the automated build capabilities of Palette Edgematic to convert visual representations of the pipeline to executable code with the push of a button;
-
Convert ML pipelines to demonstrable proofs of concept in as little as five minutes, speeding the concept to production deployment and reducing time to market.
“Only SiMa provides unparalleled innovation for the embedded edge. The release of Palette Edgematic together with our continued dominance in leading the industry in FPS/W performance is a force – we are setting a new standard in simplifying edge ML once and for all,” said founder and CEO Krishna Rangasayee. “SiMa is laser focused on removing any friction or obstacles for organizations looking to embed AI and ML into their products and services. In fact, if we do our job right, nobody doing edge ML should ever have to resort to embedded hand coding again.”
Palette Edgematic is a free visual extension of SiMa.ai’s Palette software platform for end-to-end application development, of which the production (1.0) version was recently released. Powered remotely by SiMa.ai MLSoC, the initial release of Palette Edgematic delivers a GUI based visual experience to evaluate five optimized pipelines and 40 different models covering object detection, tracking, classification, semantic segmentation and instance segmentation use cases
.
“While machine learning has been widely deployed in the cloud, ML adoption at the edge has been very slow due to lack of easy to use software tools. Customers have to hand optimize models and the entire end to end application to get necessary performance and accuracy. It typically takes multiple weeks to evaluate and several months to deploy ML applications,” said Gopal Hegde, Senior Vice President of Engineering and Operations at SiMa.ai “Our Palette Edgematic software provides a no code visual GUI platform that enables customers to evaluate our MLSoC platform in a few hours. Over time, customers with no ML development experience can develop, fine tune, deploy and scale ML applications quickly, democratizing ML at the embedded edge.”
“The transformative impact of machine learning is here to stay, and nowhere is this more apparent or exciting than what lies ahead for the possibilities at the edge,” said Karl Freund, Founder and Principal Analyst at Cambrian-AI Research. “Execution of high-performance software is not always the case with semi and edge companies. What SiMa has introduced with Palette Edgematic will rapidly fuel innovation by giving any organization the power to see what’s possible at the edge through the testing and optimizing of their applications, and significantly accelerating their time to deployment. The company is delivering on its promise to put software first.”
“SiMa’s Palette command line tools are very productive, but Palette Edgematic takes efficiency to a whole new level. I can start with SiMa’s optimized building blocks, add our special sauce blocks, then easily drag and drop them together to create and test pipelines in a fraction of the time it has taken in legacy embedded design environments,” said Luke Liu, CEO of LIPS-HCL. “I see our LIPS proven algorithms quickly becoming solution libraries we can monetize, with customers able to evaluate, customize and deploy without a lot of consulting with our team, freeing us to develop and expand our supported use cases. A real game changer in embedded computer vision application development!”
Current SiMa.ai Palette customers will automatically receive access to Palette Edgematic and prospective customers can apply for access to Palette Edgematic 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.
