π§ UNDER CONSTRUCTION π§ο
Welcome to itwinaiβs documentation!ο
itwinai
is a framework for advanced AI/ML workflows in Digital Twins (DTs).
This platform is intended to support general-purpose MLOps for Digital Twin use cases in the interTwin project.
Platform for machine learning workflows in digital twinsο
The goal of this platform is to provide ML researchers with an easy-to-use endpoint to manage general-purpose ML workflows, with limited engineering overhead, while providing state-of-the-art MLOps best practices.
The user can fully describe ML workflows for DT applications by providing a set of configuration files as input.
The itwinai
platform instantiates ML workflows with the configurations provided by the DT developer.
The execution of ML workflows outputs a set of ML metrix, which are visualised by itwinai
via MLFlow.
The trained ML model that performed best on the validation dataset is saved to the Models Registry for future predictions.
In itwinai
platform, we focus mainly on the MLOps step, simulating or oversimplifying the rest (e.g., pre-processing, authentication, workflow execution).