tinyML Talks on April 5, 2022 “AutoFlow - an open source Framework to automatically implement neural networks on embedded devices” by Daniel Konegen and Marcus Rüb

We held our next tinyML Talks webcast. Daniel Konegen and Marcus Rüb from Hahn-Schickard presented AutoFlow - an open source Framework to automatically implement neural networks on embedded device on April 5, 2022.

AutoFlow is a tool that helps developers to implement machine learning (ML) faster and easier on embedded devices. The whole workflow of a data scientist should be covered. Starting from building the ML model to the selection of the target platform to the optimization and implementation of the model on the target platform. To realize these functions, AutoFlow was divided into two parts. One part represents the automatic generation of neural networks. This is realized by using Automated machine learning (AutoML). For a given data set, different neural networks are automatically trained, from which the one that achieves the highest accuracy is stored. In the other part of AutoFlow, neural networks can be reduced in size using pruning and quantization. Also, the target platform on which the model is to be executed later can be selected. Accordingly, the model is converted and the necessary files are generated for execution on the target platform. AutoFlow is an open-source tool and can be downloaded from GitHub.
The Tool is available at: GitHub - Hahn-Schickard/AutoFlow: Bring your AI to the Edge - Starting from building the ML model to the selection of the target platform to the optimization and implementation of the model on the target platform.

Daniel Konegen studied Mechanical Engineering and Mechatronics (B.Sc.) and Mechatronic Systems (M.Sc.) at Furtwangen University. In his master’s thesis, he worked on the automated implementation of neural networks on embedded systems. After completing his Master’s degree in 2020, he worked at the Karlsruhe Institute of Technology at the Institute of Telematics from October 2020 to August 2021. Since September 2021, he has been responsible for the areas of embedded AI and data science at Hahn-Schickard.

Marcus Rüb studied electrical engineering (B.Sc.) and mechatronic systems (M.Sc.) at Furtwangen University from 2015 to 2020. Since 2018, he has been employed at Hahn-Schickard as a research assistant and conducts research in the field of TinyML. He is currently doing his PhD at the Technical University of Munich.

=========================

Watch on YouTube:
Daniel Konegen and Marcus Rüb

Download presentation slides:
Daniel Konegen and Marcus Rüb

Feel free to ask your questions on this thread and keep the conversation going!