Residual_Image_Learning_GAN

KO | EN

gitlite — search

#python #ai #typescript #llm #machine-learning #rust #linux #macos #java #kubernetes #vue #pytorch #security #open-source

Residual_Image_Learning_GAN

(★ 28)

Tensorflow implementation for Paper "Learning Residual Images for Face Attribute Manipulation"

Residual_Image_Learning_GAN Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Residual_Image_Learning_GAN
Tensorflow Implement of Paper [Learning Residual Images for Face Attribute Manipulation](https://arxiv.org/abs/1612.05363), which has been accepted in CVPR 2017. We need implement this paper and compare our results with that, because Auther does't public their code. I think this paper is a good paper and they give a perfect idea for facial visual manipulating with images residual learning. This difference with original paper is that this implements use Instance_norm instead of batch_normal. You can adjust important weights for getting more perfect results.

![image](https://raw.githubusercontent.com/zhangqianhui/Residual_Image_Learning_GAN/master/imgs/paper_caption.PNG)

## Prerequisites

+ [Tensorflow](http://tensorflow.org/)

## Datasets
We use the [CelebA](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html) datasets. The code will crop and resize images to 128x128.

~~~
---------------------------------------------
The training data folder should look like : 
<train_data_root>
                |--image1
                |--image2
                |--image3
                |--image4...
---------------------------------------------
~~~

## Running

$ python main.py --IMAGE_PATH /home/?/data/celebA/
 
## Experiments

Male face:

![](https://raw.githubusercontent.com/zhangqianhui/Residual_Image_Learning_GAN/master/imgs/m.png)

The residual face:

![](https://raw.githubusercontent.com/zhangqianhui/Residual_Image_Learning_GAN/master/imgs/m_r.png)

Man-to-Woman Face:

![](https://raw.githubusercontent.com/zhangqianhui/Residual_Image_Learning_GAN/master/imgs/m_wm.png)

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

Female face:

![](https://raw.githubusercontent.com/zhangqianhui/Residual_Image_Learning_GAN/master/imgs/wm.png)

The residual face:

![](https://raw.githubusercontent.com/zhangqianhui/Residual_Image_Learning_GAN/master/imgs/wm_r.png)

Woman-to-Man Face:

![](https://raw.githubusercontent.com/zhangqianhui/Residual_Image_Learning_GAN/master/imgs/wm_m.png)

## Acknowledgement
+ [DCGAN-tensorflow](https://github.com/carpedm20/DCGAN-tensorflow)

Residual_Image_Learning_GAN

Residual_Image_Learning_GAN Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Residual_Image_Learning_GAN

Residual_Image_Learning_GAN Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README