Abstract
The paper considers the quantization of weights as a tool for reducing the original size of an already trained neural net without having to perform the retraining. We have examined the methods based on uniform and exponential weight quantization and compared the results. Besides, we demonstrate the use of the quantization algorithm in three neural nets: VGG16, VGG19 and ResNet50.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). https://arxiv.org/abs/1409.1556
ImageNet – huge image dataset. http://www.image-net.org
Zhu, C., Han, S., Mao, H., Dally, W.J.: Trained ternary quantization. https://arxiv.org/abs/1612.01064
Zhou, S., Ni, Z., Zhou, X., Wen, H., Wu, Y., Zou, Y.: Dorefa-net: training low bitwidth convolutional neural networks with low bitwidth gradients. https://arxiv.org/pdf/1606.06160.pdf
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. CoRR. https://arxiv.org/abs/1010.00149, February 2015
Cai, J., Takemoto, M., Nakajo, H.: A deep look into logarithmic quantization of model parameters in neural networks. In: The 10th International Conference on Advances in Information Technology (IAIT2018), Bangkok, Thailand, 10–13 December 2018, 8 pages. ACM, New York (2018). https://doi.org/10.1145/3291280.3291800
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
The work financially supported by State Program of SRISA RAS No. 0065-2019-0003 (AAA-A19-119011590090-2).
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Khayrov, E.M., Malsagov, M.Y., Karandashev, I.M. (2020). Post-training Quantization of Deep Neural Network Weights. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research III. NEUROINFORMATICS 2019. Studies in Computational Intelligence, vol 856. Springer, Cham. https://doi.org/10.1007/978-3-030-30425-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-30425-6_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30424-9
Online ISBN: 978-3-030-30425-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)