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

A Dynamic Adjustment Method Based on DCGAN Performance

A dynamic adjustment and performance technology, applied in neural learning methods, neural architectures, biological neural network models, etc., can solve problems such as network model collapse, discriminator ability improvement limitations, small gradient values, etc., to ensure robustness and avoid patterns Crash, robust effects

Active Publication Date: 2020-11-24
SOUTH CHINA UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is worth noting that there is no unified measure of the "ability" of the generator and discriminator, which means that the training of the entire network can continue indefinitely
In the initial stage of training, the abilities of both parties are constantly improving, but as the number of training increases, the overlap rate of the input samples of the generator will continue to increase, and the gradient value will become smaller and smaller, that is, it is difficult to further improve the ability. Limited, the quality of the image input to the discriminator has not been improved, and the ability to improve the discriminator is also limited
With the continuous training of the network, the generator will also appear to be overfitting, that is, when the text in the data set is input, the quality of the generated image is very good, but once the user is allowed to input the text description, the quality of the generated image is difficult to obtain ensure
Although the loss function is defined, there is no quantitative evaluation standard based on parameters such as the loss function and the number of training times, and the loss functions of both parties have not been unified in the overall framework, that is, there is no ability to combine the generator and the discriminator. Linked together to describe, that is, the measurement standard of the entire network framework is missing
The result of this state of lack of an evaluation standard mechanism is that the entire network is endlessly trained
More importantly, there is no balanced criterion for the capabilities of the generator and the discriminator, so that during the training process, the ability of one will far exceed the other, resulting in the collapse of the entire network 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
  • A Dynamic Adjustment Method Based on DCGAN Performance
  • A Dynamic Adjustment Method Based on DCGAN Performance
  • A Dynamic Adjustment Method Based on DCGAN Performance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] This embodiment discloses a dynamic adjustment method based on DCGAN performance, which specifically includes the following steps:

[0039] Step S1, using the deep convolutional neural network CNN as the generative confrontation network GAN of the generator and discriminator, and constructing the deep convolutional generative confrontation network DCGAN.

[0040] In the GAN framework proposed by GoodFellow, any differentiable function can function as a generator and a discriminator. The generative confrontation network GAN using the convolutional neural network CNN as the generator and the discriminator is DCGAN. attached by figure 1 It can be seen that the image is input to the generator, and after a series of transposed convolutions, it gradually changes from low-dimensional to high-dimensional, and finally outputs an image that conforms to the dimension. Throughout the process, nonlinear layers and batch normalization are applied after each neural network layer.

...

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 discloses a dynamic adjustment method based on DCGAN performance, which belongs to the field of deep learning signal processing. The dynamic adjustment method includes the following steps: S1, constructing a deep convolution generation confrontation network DCGAN; S2, using an image data set to perform network Training; S3, using the network loss function to define the performance of the generator and the discriminator; S4, defining the ability of the network to generate images according to the performance of the generator and the discriminator; S5, monitoring the network training in real time to realize the dynamic adjustment of the network performance. This method can monitor the performance of DCGAN in real time, realize the dynamic adjustment of the network's ability to generate images, ensure the balanced improvement of the generator and discriminator capabilities, and avoid the "mode collapse" in the network training process, so that The quality of images generated by DCGAN is guaranteed.

Description

technical field [0001] The invention relates to the technical field of deep learning signal processing, in particular to a dynamic adjustment method based on DCGAN performance. Background technique [0002] Generative Adversarial Network (GAN for short) is a framework proposed by Goodfellow in 2014. It is based on the idea of ​​"game theory" and constructs two models of generator (generator) and discriminator (discriminator). Uniform noise of (0, 1) or Gaussian random noise generates images, and the latter discriminates the input image to determine whether it is an image from the dataset or an image produced by the generator. Every time the discriminator completes a judgment, it returns the result error to the generator. Using the return error of the discriminator, the generator further improves its own model to generate higher-quality images. When the generator cannot distinguish whether the image comes from the data set or the generator, it is considered that the generato...

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 Patents(China)
IPC IPC(8): G06N3/08G06N3/04
CPCG06N3/08G06N3/045
Inventor 周智恒李立军
Owner SOUTH CHINA UNIV OF TECH
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