Method and device for compressing and decompressing neural network model

A neural network model and decompression technology, applied in the field of compressing and decompressing neural network models, can solve the problems of many neural network model parameters, complex neural network model structure, and neural network model occupying large storage resources, etc., so as to improve the compression effect. Effect

Pending Publication Date: 2022-02-22
HUAWEI TECH CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the structure of the neural network model is relatively complex, and the parameters of the neur

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 device for compressing and decompressing neural network model
  • Method and device for compressing and decompressing neural network model
  • Method and device for compressing and decompressing neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0083] Embodiments of the present application provide a method and device for compressing and decompressing a neural network model, which are used to reduce the occupation of storage resources by the neural network model.

[0084] The embodiments of the present application may be applied to computer devices with limited storage space. Wherein, the computer equipment may be a vehicle-mounted terminal, a dialogue robot, and some portable terminal equipment.

[0085] Taking the vehicle-mounted terminal as an example, as shown in Figure 1(a), in the scene of automatic driving or assisted parking, environmental data such as the road conditions around the vehicle are collected through sensors such as cameras, and then the driving controller (a type of vehicle-mounted terminal) ) to run the neural network model to process the environmental data, so as to realize automatic driving or assisted parking. Due to the complex structure and many parameters of the neural network model, it wi...

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

The embodiment of the invention discloses a method and equipment for compressing and decompressing a neural network model, which are used for reducing the occupation of the neural network model on storage resources. The method comprises the steps of obtaining M to-be-compressed data set, wherein each to-be-compressed data set comprises the actual value of at least one parameter of a neural network model, and M is an integer larger than 1; and compressing the actual value of each parameter in the M to-be-compressed data sets according to the M different target compression parameters to obtain M compressed data sets, each compressed data set comprising a compressed value of at least one parameter of the neural network model, and the M different target compression parameters being in one-to-one correspondence with the M to-be-compressed data sets.

Description

technical field [0001] The embodiments of the present application relate to the technical field of artificial intelligence, and in particular to a method and device for compressing and decompressing a neural network model. Background technique [0002] With the advancement and development of science and technology, the influence of artificial intelligence is increasing. In recent years, with the advancement of related technologies, artificial intelligence technology has also entered a stage of rapid development. Compared with other artificial intelligence techniques, the neural network method has higher accuracy, but there are also shortcomings. For example, the structure of the neural network model is relatively complex, and the parameters of the neural network model are many, so that the neural network model needs to occupy a large amount of storage resources. [0003] Therefore, a method for compressing the neural network model is needed to reduce the storage resources ...

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
IPC IPC(8): G06N3/08
CPCG06N3/082
Inventor 夏文胡甄博邹翔宇曹建龙陶喆
Owner HUAWEI TECH CO LTD
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