Open and code-free software raises productivity for AI edge deployments
Claimed to be the industry’s first open and code-free software platform to span the complete edge AI operational workflow from idea to development, deployment and management, AI Studio is by Blaize. The company says it dramatically reduces edge AI application deployment complexity, time, and cost by breaking the barriers within existing application development and machine learning operations (MLOps) infrastructure. It eliminates the complexities of integrating disparate tools and workflows, and introduces multiple ease-of-use and intelligence features. According to Blaize, AI Studio reduces models moving to deployment to months from days.
AI studio introduces user interface, collaborative marketplaces, end-to-end application development and operational management. It can be deployed with the Blaize AI edge computing hardware for application development and MLOps.
The AI Studio code-free visual interface is intuitive, with speech commands such as “Hey Blaize” to summon a contextually intelligent assistant with an expert knowledge-driven recommendation system to guide users through the workflow.
Users can deploy models with one click to plug into any workflow across multiple open standards including ONNX, OpenVX, containers, Python, or GStreamer. According to Blaize, no other solution offers the same degree of open standard deployment support, as most are proprietary and lock in users with limited options. Support for these open standards allows AI Studio to deploy to any hardware that fully supports the standards.
Marketplaces support allows users to discover models, data and complete applications from public or private networks and to collaborate continuously to build and deploy AI applications.
AI Studio supports open public models, data marketplaces and repositories, and provides connectivity and infrastructure to host private marketplaces. Users can continually scale proven AI edge models and vertical AI solutions to effectively reuse across enterprises, choosing from hundreds of models with drag and drop ease to speed application development
The AI Studio model development workflow allows users to easily train and optimise models for specific datasets and use cases, and deploy quickly into multiple formats and packages. Its Transfer Learning feature quickly retrains imported models for the user’s data and use case. Another feature is the edge-aware optimisation tool, NetDeploy, which automatically optimises the models to the user’s specific accuracy and performance needs. Users can build and customise complete application flows other than neural networks, such as image signal processing, tracking or sensor fusion functions.
AI Studio helps users deploy, manage, monitor and continuously improve their edge AI applications. It is built on a cloud-native infrastructure based on microservices, containers and Kubernetes, for scalable and reliable production, says Blaize.
Application areas are smart retail, smart city and industry 4.0 projects. AI Studio is available now to qualified early adopter customers, with general availability in Q1 2021. The AI Studio product offering includes licenses for individual seats, enterprise, and on-premise subscriptions, with product features and services suited to the needs of each license type.
