Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Compression method and device of deep learning model, equipment and storage medium

A deep learning and compression method technology, applied in the computer field, can solve problems such as the influence of model prediction effect, and achieve the effect of saving loading time, improving computing speed, and increasing computing speed.

Pending Publication Date: 2021-05-21
MASHANG CONSUMER FINANCE CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, pruning the model may affect the prediction effect of the model

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
  • Compression method and device of deep learning model, equipment and storage medium
  • Compression method and device of deep learning model, equipment and storage medium
  • Compression method and device of deep learning model, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0026] The terms "first", "second", and "third" in this application are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, features defined as "first", "second", and "third" may explicitly or implicitly include at least one of these features. In the description of the present application, "plurality" means at least t...

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 compression method and device of a deep learning model, equipment and a storage medium. The compression method comprises the following steps: modifying original formats of partial graph nodes in a pre-trained initial deep learning model into preset formats; and converting the data type of the graph node of which the format is the preset format into integer data from floating-point data so as to compress the initial deep learning model. Therefore, the operation rate can be improved, the model size is reduced, and the prediction effect of the model is not affected.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a compression method, device, equipment and storage medium of a deep learning model. Background technique [0002] The deep learning model refers to the neural network that has been trained, and the network contains a large number of parameters to record the characteristic information of the training data. [0003] At present, due to the large number of nodes and parameters in the deep learning model, the final trained model needs to consume huge memory and calculation costs; for this reason, people generally prune the model to remove unimportant parameters in the model To reduce the redundancy of the model, thereby increasing the computing speed and reducing the model volume. [0004] However, pruning the model may affect the prediction effect of the model. Contents of the invention [0005] The present application provides a compression method, device, equipment, ...

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
CPCG06N3/082G06N3/045
Inventor 黄磊杨春勇靳丁南权圣
Owner MASHANG CONSUMER FINANCE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products