Accurate yet efficient Deep Neural Networks (DNNs) are in high demand, especially for applications that require their execution on constrained edge devices. Finding such DNNs in a reasonable time for new applications requires automated optimization pipelines since the huge space of hyper-parameter combinations is impossible to explore extensively by hand. In this work, we propose PLiNIO, an open-source library implementing a comprehensive set of state-of-the-art DNN design automation techniques, all based on lightweight gradient-based optimization, under a unified and user-friendly interface. With experiments on several edge-relevant tasks, we show that combining the various optimizations available in PLiNIO leads to rich sets of solutions that Pareto-dominate the considered baselines in terms of accuracy vs model size. Noteworthy, PLiNIO achieves up to 94.34% memory reduction for a <1% accuracy drop compared to a baseline architecture.
@article{arxiv.2307.09488,
title = {PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization},
author = {Daniele Jahier Pagliari and Matteo Risso and Beatrice Alessandra Motetti and Alessio Burrello},
journal= {arXiv preprint arXiv:2307.09488},
year = {2023}
}
Comments
Accepted at the 2023 Forum on Specification & Design Languages (FDL)