Patent · US Active

Method and apparatus for compressing deep learning model

US11681920B2 · kind B2 · utility

0Cited by

0References

12Claims

0Family size

Assignee

BAIDU USA LLC · US

Inventors

Zhiyu Cheng · Sunnyvale, US
Yingze Bao · Beijing, CN

Key dates

Filing date	Sep 27, 2019
Grant date	Jun 20, 2023
Priority date	—
Expiry date	Dec 17, 2041

Classification

Technology area (CPC H)Electricity
CPC primaryH03M7/702
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Embodiments of the present disclosure disclose a method and apparatus for compressing a deep learning model. An embodiment of the method includes: acquiring a to-be-compressed deep learning model; pruning each layer of weights of the to-be-compressed deep learning model in units of channels to obtain a compressed deep learning model; and sending the compressed deep learning model to a terminal device, so that the terminal device stores the compressed deep learning model. By pruning each layer of weights of the deep learning model in units of channels, the parameter redundancy of the deep learning model is effectively reduced, thereby improving the computational speed of the deep learning model and maintaining the model accuracy.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.