Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/carpedm20/dcgan-tensorflow

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
https://github.com/carpedm20/dcgan-tensorflow

dcgan gan generative-model tensorflow

Last synced: 3 days ago
JSON representation

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

Host: GitHub
URL: https://github.com/carpedm20/dcgan-tensorflow
Owner: carpedm20
License: mit
Created: 2015-12-11T02:06:40.000Z (about 9 years ago)
Default Branch: master
Last Pushed: 2021-01-06T05:38:06.000Z (almost 4 years ago)
Last Synced: 2024-12-18T20:06:17.431Z (3 days ago)
Topics: dcgan, gan, generative-model, tensorflow
Language: JavaScript
Homepage: http://carpedm20.github.io/faces/
Size: 76.2 MB
Stars: 7,158
Watchers: 245
Forks: 2,625
Open Issues: 188
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # DCGAN in Tensorflow

Tensorflow implementation of [Deep Convolutional Generative Adversarial Networks](http://arxiv.org/abs/1511.06434) which is a stabilize Generative Adversarial Networks. The referenced torch code can be found [here](https://github.com/soumith/dcgan.torch).

![alt tag](DCGAN.png)

* [Brandon Amos](http://bamos.github.io/) wrote an excellent [blog post](http://bamos.github.io/2016/08/09/deep-completion/) and [image completion code](https://github.com/bamos/dcgan-completion.tensorflow) based on this repo.

* *To avoid the fast convergence of D (discriminator) network, G (generator) network is updated twice for each D network update, which differs from original paper.*

## Online Demo

[](http://carpedm20.github.io/faces/)

[link](http://carpedm20.github.io/faces/)

## Prerequisites

- Python 2.7 or Python 3.3+

- [Tensorflow 0.12.1](https://github.com/tensorflow/tensorflow/tree/r0.12)

- [SciPy](http://www.scipy.org/install.html)

- [pillow](https://github.com/python-pillow/Pillow)

- [tqdm](https://pypi.org/project/tqdm/)

- (Optional) [moviepy](https://github.com/Zulko/moviepy) (for visualization)

- (Optional) [Align&Cropped Images.zip](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html) : Large-scale CelebFaces Dataset

## Usage

First, download dataset with:

    $ python download.py mnist celebA

To train a model with downloaded dataset:

    $ python main.py --dataset mnist --input_height=28 --output_height=28 --train

    $ python main.py --dataset celebA --input_height=108 --train --crop

To test with an existing model:

    $ python main.py --dataset mnist --input_height=28 --output_height=28

    $ python main.py --dataset celebA --input_height=108 --crop

Or, you can use your own dataset (without central crop) by:

    $ mkdir data/DATASET_NAME

    ... add images to data/DATASET_NAME ...

    $ python main.py --dataset DATASET_NAME --train

    $ python main.py --dataset DATASET_NAME

    $ # example

    $ python main.py --dataset=eyes --input_fname_pattern="*_cropped.png" --train

If your dataset is located in a different root directory:

    $ python main.py --dataset DATASET_NAME --data_dir DATASET_ROOT_DIR --train

    $ python main.py --dataset DATASET_NAME --data_dir DATASET_ROOT_DIR

    $ # example

    $ python main.py --dataset=eyes --data_dir ../datasets/ --input_fname_pattern="*_cropped.png" --train

    

## Results

![result](assets/training.gif)

### celebA

After 6th epoch:

![result3](assets/result_16_01_04_.png)

After 10th epoch:

![result4](assets/test_2016-01-27%2015:08:54.png)

### Asian face dataset

![custom_result1](web/img/change5.png)

![custom_result1](web/img/change2.png)

![custom_result2](web/img/change4.png)

### MNIST

MNIST codes are written by [@PhoenixDai](https://github.com/PhoenixDai).

![mnist_result1](assets/mnist1.png)

![mnist_result2](assets/mnist2.png)

![mnist_result3](assets/mnist3.png)

More results can be found [here](./assets/) and [here](./web/img/).

## Training details

Details of the loss of Discriminator and Generator (with custom dataset not celebA).

![d_loss](assets/d_loss.png)

![g_loss](assets/g_loss.png)

Details of the histogram of true and fake result of discriminator (with custom dataset not celebA).

![d_hist](assets/d_hist.png)

![d__hist](assets/d__hist.png)

## Related works

- [BEGAN-tensorflow](https://github.com/carpedm20/BEGAN-tensorflow)

- [DiscoGAN-pytorch](https://github.com/carpedm20/DiscoGAN-pytorch)

- [simulated-unsupervised-tensorflow](https://github.com/carpedm20/simulated-unsupervised-tensorflow)

## Author

Taehoon Kim / [@carpedm20](http://carpedm20.github.io/)