Framework to Evaluate Deep Learning Algorithms for Edge Inference and Training

Tiberius-George Sorescu, Chandrakanth R. Kancharla, Jeroen Boydens, Hans Hallez, Mathias Verbeke

Abstract: Edge computing is a paradigm in which data is intelligently processed close to its source. Along with advancements in deep learning, there is a growing interest in using deep neural networks at the edge for predictive analytics. Given the realistic constraints in computational resources of edge devices, this combination is challenging. In order to bridge the gap between deep learning models and efficient edge analytics, a container-based framework is presented that evaluates user-specified deep learning models for efficiency on the edge. The proposed framework is validated on a rotating machinery fault diagnosis use case. Conclusions on efficient state-of-the-art models for rotating machine fault diagnosis were drawn and appropriately reported.