https://github.com/mingtaoguo/deep-image-analogy-tensorflow

Implementation of the paper : Deep image analogy
https://github.com/mingtaoguo/deep-image-analogy-tensorflow

image-analogy tensorflow tensorflow-gpu vgg19

Last synced: 3 months ago
JSON representation

Implementation of the paper : Deep image analogy

• Host: GitHub
• URL: https://github.com/mingtaoguo/deep-image-analogy-tensorflow
• Owner: MingtaoGuo
• License: mit
• Created: 2018-10-15T09:29:05.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2018-10-21T14:52:00.000Z (almost 7 years ago)
• Last Synced: 2025-04-05T13:11:21.445Z (6 months ago)
• Topics: image-analogy, tensorflow, tensorflow-gpu, vgg19
• Language: Python
• Homepage:
• Size: 248 KB
• Stars: 35
• Watchers: 2
• Forks: 8
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Deep-image-analogy-TensorFlow

Implementation of the paper : Deep image analogy

# Introduction

This code mainly implements the interesting paper [Visual Attribute Transfer through Deep Image Analogy](http://cn.arxiv.org/pdf/1705.01088), details of the algorithm please see the paper. 

![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/suanfa.jpg)

# How to use 

------------------------------------------------------

Step 1. Download the vgg19.npy([BaiduDrive](https://pan.baidu.com/s/1V6JOGJ5O2rabZ_ZLdCF30w)), and put it into the folder 'vgg19'

Step 2. Modify the image's path in Main.py

Step 3. execute Main.py

--------------------------------------------------------

# Python packages

===================

1. python 3.5

2. tensorflow1.4.0

3. numpy

4. scipy

5. pillow

===================

# Results

|Input|:|Output|::|Output|:|Input|

|-|-|-|-|-|-|-|

|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/girl_A.jpg)|:|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/girl_A_prime.jpg)|::|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/girl_B.jpg)|:|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/girl_B_prime.jpg)|

|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/wlh.jpg)|:|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/wlh_prime.jpg)|::|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/catong_prime.jpg)|:|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/catong.jpg)|

|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/sumiao.jpg)|:|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/lanse_prime.jpg)|::|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/sumiao_prime.jpg)|:|![](https://github.com/MingtaoGuo/Deep-image-analogy-TensorFlow/blob/master/IMAGES/lanse.jpg)|

#### Time: 3 minutes for 224x224 image size

#### These results are not satisfactory compare to paper's attractive results

# Acknowledgement

Thanks for the PatchMatch code from [harveyslash](https://github.com/harveyslash/PatchMatch)