Key takeaways
- SiMa.ai's Palette Edgematic accelerates ML app deployment from weeks to minutes through a no-code approach.
- The software features a drag-and-drop interface, enabling users to create and deploy ML models effortlessly.
- It allows real-time evaluation of performance and power consumption for edge ML applications.
- Palette Edgematic simplifies prototyping and performance iteration without the need for extensive coding.
- The tool converts visual pipeline designs into executable code with a single button click.
SiMa.ai released Palette Edgematic to accelerate machine learning applications at the embedded edge. This debut delivers an on-ramp to AI and ML via its ‘no-code’ approach to create and fine-tune ML applications from anywhere via a web browser in no time.
Palette Edgematic enables a “drag and drop” feature – a code-free approach, where users can create and deploy their models and complete computer vision pipelines automatically within minutes. It provides a direct path to implementation at the edge, eliminating the need for an intermediate step in the cloud. Users can also evaluate the performance and power consumption needs of their edge ML application in real time.
The software is a free visual development environment designed for any organisation to get started and accelerate ML at the edge. It usually takes multiple weeks to evaluate and several months to deploy ML applications as customers have to hand optimise models and the entire end-to-end applications to get necessary performance and accuracy.
“ML adoption at the edge has been slow due to the lack of easy-to-use software tools. Our Palette Edgematic software provides a no code visual GUI platform that enables customers to evaluate our MLSoC platform in a few hours,” said Gopal Hegde, senior vice president of engineering and operations at SiMa.ai.
Using Palette Edgematic, developers can prototype and evaluate ML pipelines on edge devices within minutes and use real time data streams to measure KPIs. They can use the new visual canvas to iterate design and improve pipeline performance, eliminating tedious coding transitions for edge ML implementations.
The Palette Edgematic can convert visual representations of the pipeline to executable code with the push of a button.
SiMa.ai announced earlier this week a FPA/W excellence in the most recent ML Perf. 3.1 benchmark competition where it competed against NVIDIA’s newest Jetson NX. SiMa.ai was leading by a margin of 85%. This positions them as a dominant player in the competitive world of edge AI.
