There are 5 repositories under wasserstein-gan topic.
Pytorch implementation of Wasserstein GANs with Gradient Penalty
Tensorflow Implementation on "The Cramer Distance as a Solution to Biased Wasserstein Gradients" (https://arxiv.org/pdf/1705.10743.pdf)
Keras implementation of "Image Inpainting via Generative Multi-column Convolutional Neural Networks" paper published at NIPS 2018
DCGAN and WGAN implementation on Keras for Bird Generation
Unofficial PyTorch implementation of "Progressive Growing of GANs for Improved Quality, Stability, and Variation".
Torch implementation of Wasserstein GAN https://arxiv.org/abs/1701.07875
Generating Text through Adversarial Training(GAN) using Skip-Thought Vectors
Mode collapse example of GANs in 2D (PyTorch).
Wasserstein BiGAN (Bidirectional GAN trained using Wasserstein distance)
Pure tensorflow implementation of progressive growing of GANs
In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.
TensorFlow 2.0 implementation of Improved Training of Wasserstein GANs
My implementations of deep neural networks for practice.
Improved Wasserstein GAN (WGAN-GP) application on medical (MRI) images
chainer implementation of VAE-GAN, Wasserstein GAN (WGAN), CycleGAN
Chainer implementation of the Wesserstein GAN
Metropolis-Hastings GAN in Tensorflow for enhanced generator sampling
Source code for "Training Generative Adversarial Networks Via Turing Test".
A conditional Wasserstein Generative Adversarial Network with gradient penalty (cWGAN-GP) for stochastic generation of galaxy properties in wide-field surveys
Vanilla GAN and WGAN implementations in PyTorch on the FashionMNIST dataset
PyTorch implementation of Wasserstein GAN paper
Keras implementation of WGAN GP for face generation. The model is trained on CelebA dataset.
Implementation of Wasserstein Generative Adversarial Networks using Tensorflow
This repository deals with analyzing various Neural Network approaches and finding the one with the most accurate reconstruction of motion captured trajectories recorded with missing markers in softwares like Vicon Nexus
We've applied the Reptile algorithm to our GAN architectures. The peculiarity is the exclusion of G from meta-learning. Surprisingly, everything worked and the research was published in a paper. More details reported on the paper "Towards Latent Space Optimization of GANs Using Meta-Learning" and the thesis (Italian).
Brain T1-Weighted MRI Images Classification and WGAN Generation (Alzheimer's and Healthy patients) for the purpose of data augmentation. Implemented in TensorFlow, trained on ADNI dataset.