Papers
arxiv:2004.09602

Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation

Published on Apr 20, 2020
Authors:
,
,
,
,

Abstract

The review examines quantization methods for deep neural networks, focusing on 8-bit quantization techniques that maintain accuracy across various models and applications by leveraging high-throughput integer processors.

AI-generated summary

Quantization techniques can reduce the size of Deep Neural Networks and improve inference latency and throughput by taking advantage of high throughput integer instructions. In this paper we review the mathematical aspects of quantization parameters and evaluate their choices on a wide range of neural network models for different application domains, including vision, speech, and language. We focus on quantization techniques that are amenable to acceleration by processors with high-throughput integer math pipelines. We also present a workflow for 8-bit quantization that is able to maintain accuracy within 1% of the floating-point baseline on all networks studied, including models that are more difficult to quantize, such as MobileNets and BERT-large.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2004.09602 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2004.09602 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2004.09602 in a Space README.md to link it from this page.

Collections including this paper 1