Skip to main content
Have a personal or library account? Click to login
Image Transformation Based on Generative Adversarial Networks Cover
By:  and    
Open Access
|Oct 2019

Figures & Tables

Figure 1.

Data flow diagram of GAN

Figure 2.

Experimental results

NETWORK STRUCTURE OF THE DISCRIMINATOR

operationConvolution kernel sizepaceConvolution kernel numberBatch normalizationactivation function
convolution4×4264NoLeaky Relu
convolution4×42128YesLeaky Relu
convolution4×42256YesLeaky Relu
convolution4×42512YesLeaky Relu

NETWORK STRUCTURE OF THE GENERATOR

operationConvolution kernel sizepaceConvolution kernel numberBatch normalizationactivation function
convolution7×7132NoRelu
convolution3×3264YesRelu
convolution3×32128YesRelu
convolution3×32128YesRelu
convolution3×32128YesRelu
convolution3×32128YesRelu
convolution3×32128YesRelu
convolution3×32128YesRelu
deconvolution3×31/2128YesRelu
deconvolution3×31/2128YesRelu
deconvolution3×31/2128YesRelu
deconvolution3×31/2128YesRelu
deconvolution3×31/2128YesRelu
deconvolution3×31/264YesRelu
deconvolution3×31/232YesRelu
deconvolution7×713YesRelu
Language: English
Page range: 93 - 98
Published on: Oct 8, 2019
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2019 Jie Chen, Li Zhao, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.