GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → xinario → catgan_pytorch

xinario / catgan_pytorch

Licence: other
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchgenerative-adversarial-networkgandcgansemi-supervised-learningunsupervised-learningcatgan

Projects that are alternatives of or similar to catgan pytorch

Gans In Action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
Stars: ✭ 748 (+1396%)
Mutual labels:  generative-adversarial-network, gan, dcgan, semi-supervised-learning
Context Encoder
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
Stars: ✭ 731 (+1362%)
Mutual labels:  generative-adversarial-network, gan, dcgan, unsupervised-learning
Pix2pix
Image-to-image translation with conditional adversarial nets
Stars: ✭ 8,765 (+17430%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Dcgan Tensorflow
A Tensorflow implementation of Deep Convolutional Generative Adversarial Networks trained on Fashion-MNIST, CIFAR-10, etc.
Stars: ✭ 70 (+40%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Semantic image inpainting
Semantic Image Inpainting
Stars: ✭ 140 (+180%)
Mutual labels:  generative-adversarial-network, gan, dcgan
All About The Gan
All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN
Stars: ✭ 630 (+1160%)
Mutual labels:  generative-adversarial-network, gan, unsupervised-learning
Acgan Pytorch
Pytorch implementation of Conditional Image Synthesis with Auxiliary Classifier GANs
Stars: ✭ 57 (+14%)
Mutual labels:  generative-adversarial-network, gan, semi-supervised-learning
Generative adversarial networks 101
Keras implementations of Generative Adversarial Networks. GANs, DCGAN, CGAN, CCGAN, WGAN and LSGAN models with MNIST and CIFAR-10 datasets.
Stars: ✭ 138 (+176%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (+926%)
Mutual labels:  generative-adversarial-network, gan, unsupervised-learning
Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (+278%)
Mutual labels:  generative-adversarial-network, gan, unsupervised-learning
Image generator
DCGAN image generator 🖼️.
Stars: ✭ 173 (+246%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Iseebetter
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
Stars: ✭ 202 (+304%)
Mutual labels:  generative-adversarial-network, gan, unsupervised-learning
Gan Sandbox
Vanilla GAN implemented on top of keras/tensorflow enabling rapid experimentation & research. Branches correspond to implementations of stable GAN variations (i.e. ACGan, InfoGAN) and other promising variations of GANs like conditional and Wasserstein.
Stars: ✭ 210 (+320%)
Mutual labels:  generative-adversarial-network, gan, unsupervised-learning
Hypergan
Composable GAN framework with api and user interface
Stars: ✭ 1,104 (+2108%)
Mutual labels:  generative-adversarial-network, gan, unsupervised-learning
Awesome Gans
Awesome Generative Adversarial Networks with tensorflow
Stars: ✭ 585 (+1070%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (+168%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Igan
Interactive Image Generation via Generative Adversarial Networks
Stars: ✭ 3,845 (+7590%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Ssgan Tensorflow
A Tensorflow implementation of Semi-supervised Learning Generative Adversarial Networks (NIPS 2016: Improved Techniques for Training GANs).
Stars: ✭ 496 (+892%)
Mutual labels:  generative-adversarial-network, gan, semi-supervised-learning
Tensorflow Mnist Gan Dcgan
Tensorflow implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Netwokrs for MNIST dataset.
Stars: ✭ 163 (+226%)
Mutual labels:  generative-adversarial-network, gan, dcgan
Triple Gan
See Triple-GAN-V2 in PyTorch: https://github.com/taufikxu/Triple-GAN
Stars: ✭ 203 (+306%)
Mutual labels:  generative-adversarial-network, gan, semi-supervised-learning
View All Similar Projects ➔

catGAN

PyTorch implementation of Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks that was originally proposed by Jost Tobias Springenberg.

Results on CIFAR10

Note that in this repo, only the unsupervised version was implemented for now. I reaplced the orginal architecture with DCGAN and the results are more colorful than the original one.

From 0 to 100 epochs:

cifar10

Prerequisites

  • Python 2.7
  • PyTorch v0.2.0
  • Numpy
  • SciPy
  • Matplotlib

Getting Started

Installation

  • Install PyTorh and the other dependencies
  • Clone this repo:
git clone https://github.com/xinario/catgan_pytorch.git
cd catgan_pytorch

Train

  • Download the cifar10 dataset (.png format from kaggle)
  • Create a dataset folder to hold the images
mkdir -p ./datasets/cifar10/images

  • Move the extracted images into the newly created folder

  • Train a model:

python catgan_cifar10.py --data_dir ./datasets/cifar10 --name cifar10

All the generated plot and samples can be found in side ./results/cifar10

Training options

optional arguments:

--continue_train  	to continue training from the latest checkpoints if --netG and --netD are not specified
--netG NETG           path to netG (to continue training)
--netD NETD           path to netD (to continue training)
--workers WORKERS     number of data loading workers
--num_epochs EPOCHS         number of epochs to train for

More options can be found in side the training script.

Acknowledgments

Some of code are inspired and borrowed from wgan-gp, DCGAN, catGAN chainer repo

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].