carpedm20 / Began Tensorflow
Licence: apache-2.0
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"
Stars: ✭ 904
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Began Tensorflow
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+251.55%)
Mutual labels: gan, generative-model, celeba
Tensorflow DCGAN
Study Friendly Implementation of DCGAN in Tensorflow
Stars: ✭ 22 (-97.57%)
Mutual labels: gan, celeba
cgan-face-generator
Face generator from sketches using cGAN (pix2pix) model
Stars: ✭ 52 (-94.25%)
Mutual labels: gan, generative-model
Tensorlayer
Deep Learning and Reinforcement Learning Library for Scientists and Engineers 🔥
Stars: ✭ 6,796 (+651.77%)
Mutual labels: google, gan
Triple Gan
See Triple-GAN-V2 in PyTorch: https://github.com/taufikxu/Triple-GAN
Stars: ✭ 203 (-77.54%)
Mutual labels: gan, generative-model
Gan Tutorial
Simple Implementation of many GAN models with PyTorch.
Stars: ✭ 227 (-74.89%)
Mutual labels: gan, celeba
DCGAN-CelebA-PyTorch-CPP
DCGAN Implementation using PyTorch in both C++ and Python
Stars: ✭ 14 (-98.45%)
Mutual labels: gan, celeba
Tf Exercise Gan
Tensorflow implementation of different GANs and their comparisions
Stars: ✭ 110 (-87.83%)
Mutual labels: gan, celeba
Pytorch Mnist Celeba Gan Dcgan
Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets
Stars: ✭ 363 (-59.85%)
Mutual labels: gan, celeba
Tensorflow Generative Model Collections
Collection of generative models in Tensorflow
Stars: ✭ 3,785 (+318.69%)
Mutual labels: gan, generative-model
Tf.gans Comparison
Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking
Stars: ✭ 477 (-47.23%)
Mutual labels: gan, celeba
Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (-79.09%)
Mutual labels: gan, generative-model
Semantic image inpainting
Semantic Image Inpainting
Stars: ✭ 140 (-84.51%)
Mutual labels: gan, generative-model
style-vae
Implementation of VAE and Style-GAN Architecture Achieving State of the Art Reconstruction
Stars: ✭ 25 (-97.23%)
Mutual labels: generative-model, celeba
Msg Gan V1
MSG-GAN: Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn't use layer-wise growing)
Stars: ✭ 116 (-87.17%)
Mutual labels: gan, celeba
Segan
Speech Enhancement Generative Adversarial Network in TensorFlow
Stars: ✭ 661 (-26.88%)
Mutual labels: gan, generative-model
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-88.94%)
Mutual labels: gan, generative-model
Psgan
Periodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (-88.05%)
Mutual labels: gan, generative-model
Pycadl
Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"
Stars: ✭ 356 (-60.62%)
Mutual labels: gan, celeba
Seqgan
A simplified PyTorch implementation of "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient." (Yu, Lantao, et al.)
Stars: ✭ 502 (-44.47%)
Mutual labels: gan, generative-model
BEGAN in Tensorflow
Tensorflow implementation of BEGAN: Boundary Equilibrium Generative Adversarial Networks.
Requirements
- Python 2.7 or 3.x
- Pillow
- tqdm
- requests (Only used for downloading CelebA dataset)
- TensorFlow 1.3.0
Usage
First download CelebA datasets with:
$ apt-get install p7zip-full # ubuntu
$ brew install p7zip # Mac
$ python download.py
or you can use your own dataset by placing images like:
data
└── YOUR_DATASET_NAME
├── xxx.jpg (name doesn't matter)
├── yyy.jpg
└── ...
To train a model:
$ python main.py --dataset=CelebA --use_gpu=True
$ python main.py --dataset=YOUR_DATASET_NAME --use_gpu=True
To test a model (use your load_path
):
$ python main.py --dataset=CelebA --load_path=CelebA_0405_124806 --use_gpu=True --is_train=False --split valid
Results
gamma=0.5
after 300k steps
Generator output (64x64) with
gamma=0.5
after 200k steps
Generator output (128x128) with
gamma=0.5
after 300k steps
Interpolation of Generator output (64x64) with
gamma=0.5
after 200k steps
Interpolation of Generator output (128x128) with
Interpolation of Discriminator output of real images
Related works
Author
Taehoon Kim / @carpedm20
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].