DCGAN in Tensorflow

Tensorflow implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networks. The referenced torch code can be found here.

alt tag

Brandon Amos wrote an excellent blog post and image completion code 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

link

Prerequisites

Python 2.7 or Python 3.3+
Tensorflow 0.12.1
SciPy
pillow
tqdm
(Optional) moviepy (for visualization)
(Optional) Align&Cropped Images.zip : 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

celebA

After 6th epoch:

result3

After 10th epoch:

result4

Asian face dataset

custom_result1

custom_result2

MNIST

MNIST codes are written by @PhoenixDai.

mnist_result1

mnist_result2

mnist_result3

More results can be found here and here.

Training details

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

d_loss

g_loss

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

d_hist

d__hist

Related works

Author

Taehoon Kim / @carpedm20

Project Name	Stars	Repos Using This	Packages Using This	Most Recent Commit	Total Releases	Latest Release	Open Issues	License	Language
Tensorflow Examples	42,312			5 months ago			218	other	Jupyter Notebook
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
Awesome Tensorflow	16,809			3 months ago			30	cc0-1.0
TensorFlow - A curated list of dedicated resources http://tensorflow.org
Sonnet	9,515	41	11	a month ago	27	March 27, 2020	33	apache-2.0	Python
TensorFlow-based neural network library
Dcgan Tensorflow	6,761			2 years ago			183	mit	JavaScript
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
Tensorflow Tutorials	5,861			4 years ago			17		Jupyter Notebook
Simple tutorials using Google's TensorFlow Framework
Tensorflow_tutorials	5,548			a year ago			11	other	Jupyter Notebook
From the basics to slightly more interesting applications of Tensorflow
T81_558_deep_learning	5,261			a day ago			2	other	Jupyter Notebook
Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks
Cnn Text Classification Tf	5,256			3 years ago			110	apache-2.0	Python
Convolutional Neural Network for Text Classification in Tensorflow
Graph_nets	5,188	7		4 months ago	7	January 29, 2020	5	apache-2.0	Python
Build Graph Nets in Tensorflow
Topdeeplearning	4,901			3 years ago			17	mit	Python
A list of popular github projects related to deep learning

Dcgan Tensorflow