Unlock instant, AI-driven research and patent intelligence for your innovation.

Convolutional neural network model compression method, apparatus and device, and storage medium

A technology of convolutional neural network and neural network model, which is applied in the field of convolutional neural network, can solve the problem of decreased accuracy of CNN model, and achieve the effect of reducing the amount of models

Pending Publication Date: 2022-07-15
SHENZHEN HONGDIAN TECH CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present application provides a convolutional neural network model compression method, device, equipment, and storage medium, which are used to solve the problem that the accuracy of the CNN model will be reduced by the existing model compression method

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
  • Convolutional neural network model compression method, apparatus and device, and storage medium
  • Convolutional neural network model compression method, apparatus and device, and storage medium
  • Convolutional neural network model compression method, apparatus and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0022] It should be understood that relational terms such as "first" and "second" etc. are used only to distinguish one entity or operation from another entity or operation and do not necessarily require or imply the existence between these entities or operations any such actual relationship or sequence. It is to be understood that, when used in this specification a...

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 belongs to the technical field of convolutional neural networks, and particularly relates to a convolutional neural network model compression method and device, equipment and a storage medium. According to the technical scheme provided by the invention, the problem that the precision of the CNN model is reduced due to an existing model compression method can be effectively solved. The method comprises the steps of performing weight quantization on an initial convolutional neural network model, replacing an activation function of the initial convolutional neural network model with a second activation function from a first activation function, and generating a second convolutional neural network model; wherein the second activation function is an activation function with training parameters, and the training parameters can be adaptively adjusted according to training data.

Description

technical field [0001] The present application belongs to the technical field of convolutional neural networks, and in particular, relates to a method, apparatus, device and storage medium for compressing a convolutional neural network model. Background technique [0002] As the number of layers and complexity of the Convolutional Neural Network (CNN) model increases, it has hundreds or even tens of millions of parameters after training. Due to the large number of parameters and the large amount of data, the entire convolution calculation process needs to consume a lot of storage and computing resources, which makes the deployment of the CNN model on smart devices more difficult, and it is even more difficult for embedded devices with low computing power. . [0003] At present, in order to reduce the computational complexity of the CNN model, the amount of the model is usually reduced by weight quantization, that is, model compression is performed to obtain better calculati...

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
CPCG06N3/082G06N3/048G06N3/045
Inventor 张小虎龚潇
Owner SHENZHEN HONGDIAN TECH CORP