caogang / Wgan Gp
Licence: mit
A pytorch implementation of Paper "Improved Training of Wasserstein GANs"
Programming Languages
python 139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Wgan Gp
WGAN GPKeras model and tensorflow optimization of 'improved Training of Wasserstein GANs'
Stars: ✭ 16 (-98.62%)
Mutual labels: wgan-gp
generative deep learningGenerative Deep Learning Sessions led by Anugraha Sinha (Machine Learning Tokyo)
Stars: ✭ 24 (-97.93%)
Mutual labels: wgan-gp
Chainer Gan LibChainer implementation of recent GAN variants
Stars: ✭ 386 (-66.72%)
Mutual labels: wgan-gp
tfworldhackathonGitHub repo for my Tensorflow World hackathon submission
Stars: ✭ 17 (-98.53%)
Mutual labels: wgan-gp
SRGAN-PyTorchA PyTorch implementation of SRGAN specific for Anime Super Resolution based on "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network". And another PyTorch WGAN-gp implementation of SRGAN referring to "Improved Training of Wasserstein GANs".
Stars: ✭ 65 (-94.4%)
Mutual labels: wgan-gp
Fun-with-MNISTPlaying with MNIST. Machine Learning. Generative Models.
Stars: ✭ 23 (-98.02%)
Mutual labels: wgan-gp
Awesome GansAwesome Generative Adversarial Networks with tensorflow
Stars: ✭ 585 (-49.57%)
Mutual labels: wgan-gp
Generative-ModelRepository for implementation of generative models with Tensorflow 1.x
Stars: ✭ 66 (-94.31%)
Mutual labels: wgan-gp
WGAN-GP-TensorFlowTensorFlow implementations of Wasserstein GAN with Gradient Penalty (WGAN-GP), Least Squares GAN (LSGAN), GANs with the hinge loss.
Stars: ✭ 42 (-96.38%)
Mutual labels: wgan-gp
speech-enhancement-WGANspeech enhancement GAN on waveform/log-power-spectrum data using Improved WGAN
Stars: ✭ 35 (-96.98%)
Mutual labels: wgan-gp
Mimicry[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.
Stars: ✭ 458 (-60.52%)
Mutual labels: wgan-gp
Pytorch-Basic-GANsSimple Pytorch implementations of most used Generative Adversarial Network (GAN) varieties.
Stars: ✭ 101 (-91.29%)
Mutual labels: wgan-gp
wgan-gpPytorch implementation of Wasserstein GANs with Gradient Penalty
Stars: ✭ 161 (-86.12%)
Mutual labels: wgan-gp
Deeplearningmugenknockでぃーぷらーにんぐを無限にやってディープラーニングでDeepLearningするための実装CheatSheet
Stars: ✭ 684 (-41.03%)
Mutual labels: wgan-gp
Tf.gans ComparisonImplementations of (theoretical) generative adversarial networks and comparison without cherry-picking
Stars: ✭ 477 (-58.88%)
Mutual labels: wgan-gp
WGAN-GP
An pytorch implementation of Paper "Improved Training of Wasserstein GANs".
Prerequisites
Python, NumPy, SciPy, Matplotlib
A recent NVIDIA GPU
A latest master version of Pytorch
Progress
-
[x] gan_toy.py : Toy datasets (8 Gaussians, 25 Gaussians, Swiss Roll).(Finished in 2017.5.8)
-
[x] gan_language.py : Character-level language model (Discriminator is using nn.Conv1d. Generator is using nn.Conv1d. Finished in 2017.6.23. Finished in 2017.6.27.)
-
[x] gan_mnist.py : MNIST (Running Results while Finished in 2017.6.26. Discriminator is using nn.Conv1d. Generator is using nn.Conv1d.)
-
[ ] gan_64x64.py: 64x64 architectures(Looking forward to your pull request)
-
[x] gan_cifar.py: CIFAR-10(Great thanks to robotcator)
Results
-
Toy Dataset
Some Sample Result, you can refer to the results/toy/ folder for details.
- 8gaussians 154500 iteration
-
Mnist Dataset
Some Sample Result, you can refer to the results/mnist/ folder for details.
-
Billion Word Language Generation (Using CNN, character-level)
Some Sample Result after 8699 epochs which is detailed in sample
I haven't run enough epochs due to that this is very time-comsuming.
He moved the mat all out clame t
A fosts of shores forreuid he pe
It whith Crouchy digcloued defor
Pamreutol the rered in Car inson
Nor op to the lecs ficomens o fe
In is a " nored by of the ot can
The onteon I dees this pirder ,
It is Brobes aoracy of " medurn
Rame he reaariod to thim atreast
The stinl who herth of the not t
The witl is f ont UAy Y nalence
It a over , tose sho Leloch Cumm
-
Cifar10 Dataset
Some Sample Result, you can refer to the results/cifar10/ folder for details.
Acknowledge
Based on the implementation igul222/improved_wgan_training and martinarjovsky/WassersteinGAN
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].