Method and device for reducing memory occupation, electronic equipment and readable storage medium

A technology of occupation and memory, which is applied in the direction of multi-program device, program control design, electrical digital data processing, etc., can solve the problem of small effect and achieve the effect of reducing memory occupation

Active Publication Date: 2019-03-19
BEIJING KUANGSHI TECH
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when multiple neural network models need to be ru

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 reducing memory occupation, electronic equipment and readable storage medium
  • Method and device for reducing memory occupation, electronic equipment and readable storage medium
  • Method and device for reducing memory occupation, electronic equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0038] Wherein, as an optional implementation manner, the splicing condition may be: the output parameter of one network model of the multiple target network models is the input parameter of another network model, and the data format of the output parameter is consistent with that of the other network model. The data format of the input parameters is the same. In this implementation manner, splicing the multiple target network models that meet the splicing condition may be: directly splicing the one network model and the other network model.

[0039] When the output parameter of one network model is the input parameter of another network model, the two network models have a sequential relationship, and the splicing between the two network models can be realized by connecting the output parameter and the input parameter. For example, the models needed to realize the task of unlocking the face are: detection model—attribute model—recognition model—live detection model. Then the det...

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 invention provides a method and a device for reducing memory occupation, electronic equipment and a readable storage medium, and the method comprises the steps that terminal equipment firstly obtains a plurality of target network models when executing the method, and then splices the target network models meeting a splicing condition to obtain at least one spliced network model; and for each spliced network model, obtaining the memory usage amount required to be occupied when each layer of network in the spliced network model runs, and then determining the maximum value in the plurality ofmemory usage amounts as the total memory usage amount of the spliced network model. When the memory is distributed to the spliced network model, only the memory with the same numerical value as the total memory occupancy amount can be distributed, and compared with the prior art, the memory occupancy amount required for running of the spliced network model is greatly reduced.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a method, device, electronic equipment, and readable storage medium for reducing memory usage. Background technique [0002] When the neural network model is running, it often needs to occupy a large amount of memory. However, the current smart terminals usually have strict memory limitations. Therefore, when the neural network model runs on the smart terminal, the realization effect of the neural network model will be limited. [0003] In order to solve this problem, the traditional method is to realize memory multiplexing between different layers in a single neural network model, so as to reduce the memory usage of the neural network model. However, when multiple neural network models need to be run on the same device, traditional methods are of little help. Therefore, there is a need for a method of reducing the memory footprint of a neural network model at runtime to a...

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): G06F9/50G06N3/02
CPCG06F9/5016G06N3/02
Inventor 张学成
Owner BEIJING KUANGSHI TECH
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