Skip to content

Variational Autoencoder trained by Feature Perceputal Loss

Notifications You must be signed in to change notification settings

houxianxu/DFC-VAE

Repository files navigation

DFC-VAE

This is the code for the paper

Deep Feature Consistent Variational Autoencoder

The paper trained a Variational Autoencoder (VAE) model for face image generation. In addition, it provided a method to manipluate facial attributes by using attribute-specific vector.

  • Pretrained model trained on CelebA dataset
  • Code for training on GPU
  • Code for different analysis

Installation

Our implementation is based on Torch and several dependencies.

After installing Torch according to this tutorial, use following code to install dependencies:

sudo apt-get install libprotobuf-dev protobuf-compiler
luarocks install loadcaffe
luarocks install https://raw.githubusercontent.com/szym/display/master/display-scm-0.rockspec
luarocks install nngraph
sudo apt-get install libmatio2
luarocks install matio
luarocks install manifold
sudo apt-get install libatlas3-base # for manifold

we use a NVIDIA GPU for training and testing, so you also need install GPU related packages

luarocks install cutorch
luarocks install cunn
luarocks install cudnn

Dataset preparation

cd celebA

Download img_align_celeba.zip from http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html under the link "Align&Cropped Images".

Download list_attr_celeba.txt for annotation.

unzip img_align_celeba.zip; cd ..
DATA_ROOT=celebA th data/crop_celebA.lua

We need pretrained VGG-19 to compute feature perceptual loss.

cd data/pretrained && bash download_models.sh && cd ../..

Training

Open a new terminal and start the server for display images in the browser

th -ldisplay.start 8000 0.0.0.0

The images can be seen at http://localhost:8000 in the browser

Training with feature perceptual loss.

DATA_ROOT=celebA th main_cvae_content.lua

Training with pixel-by-pixel loss.

DATA_ROOT=celebA th main_cvae.lua

Generate face images using pretrained Encoder and Decoder

Pretrained model

mkdir checkpoints; cd checkpoints

We provide both Encoder and Decoder

cvae_content_123_encoder.t7 and cvae_content_123_decoder.t7 trained with relu1_1, relu2_1, relu3_1 in VGG.

Reconstruction with CelebA dataset:

DATA_ROOT=celebA reconstruction=1 th generate.lua

Face images randomly generated from latent variables:

DATA_ROOT=celebA reconstruction=0 th generate.lua

Following are some examples:

## Linear interpolation between two face images
th linear_walk_two_images.lua
## Vector arithmetic for visual attributes

First preprocess the celebA dataset annotations to separate the dataset to two parts for each attribute, indicating whether containing the specific attribute or not.

cd celebA
python get_binary_attr.py
# should generate file: 'celebA/attr_binary_list.txt'
cd ..
th linear_walk_attribute_vector.lua

Here are some examples:

Better face attributes manipulation by incorporating GAN

       

       

       

Credits

The code is based on neural-style, dcgan.torch, VAE-Torch and texture_nets.

Citation

If you find this code useful for your research, please cite:

@inproceedings{hou2017deep,
  title={Deep Feature Consistent Variational Autoencoder},
  author={Hou, Xianxu and Shen, Linlin and Sun, Ke and Qiu, Guoping},
  booktitle={Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on},
  pages={1133--1141},
  year={2017},
  organization={IEEE}
}
@article{hou2019improving,
  title={Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training},
  author={Hou, Xianxu and Sun, Ke and Shen, Linlin and Qiu, Guoping},
  journal={Neurocomputing},
  volume={341},
  pages={183--194},
  year={2019},
  publisher={Elsevier},
}

About

Variational Autoencoder trained by Feature Perceputal Loss

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published