Method and apparatus for compressing deep learning model

A deep learning and model technology, applied in the computer field, can solve the problems of poor privacy, slow operation speed and high cost, and achieve the effect of reducing parameter redundancy and improving operation speed.

Pending Publication Date: 2021-03-30
BAIDU USA LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, the following two methods are usually used for head and shoulders detection: first, run the deep learning model for head and shoulders detection on the cloud, however, running the model on the cloud has problems such as high cost, high bandwidth pressure, and poor privacy; the other Second, run the deep learning model for head and shoulders detection on the terminal device. However, the existing deep learning model for head and shoulders detection is too large and has the problem of slow calculation speed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and apparatus for compressing deep learning model
  • Method and apparatus for compressing deep learning model
  • Method and apparatus for compressing deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0032] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0033] figure 1 An exemplary system architecture 100 is shown to which embodiments of the method for compressing a deep learning model or the apparatus for compressing a deep learning model of the present application can be applied.

[0034] Such as figure 1 As shown, the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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.

Description

[0001] Cross References to Related Applications [0002] This application claims the priority of the US patent application with the filing date of September 27, 2019, the application number 16 / 585,772, and the title of the invention "METHODAND APPARATUS FOR COMPRESSING DEEP LEARNING MODEL". technical field [0003] The embodiments of the present application relate to the field of computer technology, and in particular to methods and devices for compressing deep learning models. Background technique [0004] With the continuous development of artificial intelligence, the application scenarios of deep learning models are becoming more and more extensive. For example, in smart retail scenarios or other similar scenarios, smart terminal devices (terminal devices) count the number of people in a designated area by detecting people's heads and shoulders. [0005] At present, the following two methods are usually used for head and shoulders detection: first, run the deep learning ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/082G06N3/045H03M7/3059H03M7/70G06N3/063H03M7/702G06V40/10G06N3/048
Inventor 程治宇包英泽
Owner BAIDU USA LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap