Quantization of Deep Neural Networks for Accumulator-constrained Processors

Autor:	de Bruin, Barry, Zivkovic, Zoran, Corporaal, Henk
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Electrical Engineering and Systems Science - Image and Video Processing
Zdroj:	Microprocessors and Microsystems Volume 72, February 2020, 102872
Druh dokumentu:	Working Paper
DOI:	10.1016/j.micpro.2019.102872
Popis:	We introduce an Artificial Neural Network (ANN) quantization methodology for platforms without wide accumulation registers. This enables fixed-point model deployment on embedded compute platforms that are not specifically designed for large kernel computations (i.e. accumulator-constrained processors). We formulate the quantization problem as a function of accumulator size, and aim to maximize the model accuracy by maximizing bit width of input data and weights. To reduce the number of configurations to consider, only solutions that fully utilize the available accumulator bits are being tested. We demonstrate that 16-bit accumulators are able to obtain a classification accuracy within 1\% of the floating-point baselines on the CIFAR-10 and ILSVRC2012 image classification benchmarks. Additionally, a near-optimal $2\times$ speedup is obtained on an ARM processor, by exploiting 16-bit accumulators for image classification on the All-CNN-C and AlexNet networks. Comment: 20 pages, 13 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.11783 Zobrazit plný text záznamu View this record from Arxiv