Otwarty dostęp

Style Transfer Based on VGG Network

Zhe Zhao

Zhe Zhao

School of Computer Science and Engineering, Xi'an Technological UniversityXi'an, China
Wyszukaj tego autora
Sciendo|Google Scholar
Zhao, Zhe
 oraz 
Shifang Zhang

Shifang Zhang

School of Computer Science and Engineering, Xi'an Technological UniversityXi'an, China
Wyszukaj tego autora
Sciendo|Google Scholar
Zhang, Shifang
  
28 maj 2023
Style Transfer Based on VGG Network's Cover Image
O artykule
Poprzedni artykuł
Następny artykuł
Zacytuj
Pobierz okładkę
Data publikacji: 28 maj 2023
Zakres stron: 54 - 72
DOI: https://doi.org/10.2478/ijanmc-2022-0005
Słowa kluczowe
© 2022 Zhe Zhao et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

VGG Network structure.
VGG Network structure.

Figure 2.

VGG-19 network model structure.
VGG-19 network model structure.

Figure 3.

Convolution check of VGG Network and recognition ability of image semantic information.
Convolution check of VGG Network and recognition ability of image semantic information.

Figure 4.

Image after style transfer of Taipei 101 building.
Image after style transfer of Taipei 101 building.

Figure 5.

Training error (left) and test error (right) on CIFAR-10.
Training error (left) and test error (right) on CIFAR-10.

Figure 6.

Residual structure.
Residual structure.

Figure 7.

Training on ImageNet.
Training on ImageNet.

Figure 8.

Output image after style conversion.
Output image after style conversion.

Figure 9.

Encoder decoder structure.
Encoder decoder structure.

Figure 10.

Encoder decoder style transfer network structure.
Encoder decoder style transfer network structure.

Figure 11.

Style transfer image.
Style transfer image.

Figure 12.

Style images with different weights.
Style images with different weights.

Figure 13.

Night and Day switch.
Night and Day switch.

Figure 14.

Generate different style images.
Generate different style images.

Figure 1

VGG 网络结构
VGG 网络结构

Figure 2

VGG 网络模型
VGG 网络模型

Figure 3

VGG 网络的卷积检查和图像语义信息的识别能力
VGG 网络的卷积检查和图像语义信息的识别能力

Figure 4

台北 101 大厦风格迁移后的图像
台北 101 大厦风格迁移后的图像

Figure 5

CIFAR-10 上的训练错误（左）和测试错误（右）
CIFAR-10 上的训练错误（左）和测试错误（右）

Figure 6

残差结构
残差结构

Figure 7

在 ImageNet 上的训练
在 ImageNet 上的训练

Figure 8

风格迁移后的输出图像
风格迁移后的输出图像

Figure 9

编码器解码器结构
编码器解码器结构

Figure 10

编码器解码器式的传输网络结构
编码器解码器式的传输网络结构

Figure 11

风格迁移图像
风格迁移图像

Figure 12

具有不同权重的风格图像
具有不同权重的风格图像

Figure 13

夜间和日间转换
夜间和日间转换

Figure 14

生成不同风格图像
生成不同风格图像
Język:
Angielski
Częstotliwość wydawania:
4 razy w roku
Dziedziny czasopisma:
Informatyka, Informatyka, inne
Kanał RSS czasopisma