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 → anitan0925 → vaegan

anitan0925 / vaegan

Licence: MIT license
An implementation of VAEGAN (variational autoencoder + generative adversarial network).

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learninggenerative-adversarial-networkvariational-autoencoder

Projects that are alternatives of or similar to vaegan

Textbox
TextBox is an open-source library for building text generation system.
Stars: ✭ 257 (+192.05%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Repo 2017
Python codes in Machine Learning, NLP, Deep Learning and Reinforcement Learning with Keras and Theano
Stars: ✭ 1,123 (+1176.14%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Generative models tutorial with demo
Generative Models Tutorial with Demo: Bayesian Classifier Sampling, Variational Auto Encoder (VAE), Generative Adversial Networks (GANs), Popular GANs Architectures, Auto-Regressive Models, Important Generative Model Papers, Courses, etc..
Stars: ✭ 276 (+213.64%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Pytorch Rl
This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch
Stars: ✭ 394 (+347.73%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Video prediction
Stochastic Adversarial Video Prediction
Stars: ✭ 247 (+180.68%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
tt-vae-gan
Timbre transfer with variational autoencoding and cycle-consistent adversarial networks. Able to transfer the timbre of an audio source to that of another.
Stars: ✭ 37 (-57.95%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Deep Generative Models
Deep generative models implemented with TensorFlow 2.0: eg. Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Deep Boltzmann Machine (DBM), Convolutional Variational Auto-Encoder (CVAE), Convolutional Generative Adversarial Network (CGAN)
Stars: ✭ 34 (-61.36%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
lagvae
Lagrangian VAE
Stars: ✭ 27 (-69.32%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (+60.23%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
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 (+52.27%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Rectorch
rectorch is a pytorch-based framework for state-of-the-art top-N recommendation
Stars: ✭ 121 (+37.5%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
deep-blueberry
If you've always wanted to learn about deep-learning but don't know where to start, then you might have stumbled upon the right place!
Stars: ✭ 17 (-80.68%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
precision-recall-distributions
Assessing Generative Models via Precision and Recall (official repository)
Stars: ✭ 80 (-9.09%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
Generative Continual Learning
No description or website provided.
Stars: ✭ 51 (-42.05%)
Mutual labels:  generative-adversarial-network, variational-autoencoder
GAN-Anime-Characters
Applied several Generative Adversarial Networks (GAN) techniques such as: DCGAN, WGAN and StyleGAN to generate Anime Faces and Handwritten Digits.
Stars: ✭ 43 (-51.14%)
Mutual labels:  generative-adversarial-network
BicycleGAN-pytorch
Pytorch implementation of BicycleGAN with implementation details
Stars: ✭ 99 (+12.5%)
Mutual labels:  generative-adversarial-network
CartoonGAN-tensorflow
Simple code implement the paper of CartoonGAN(CVPR2018)
Stars: ✭ 14 (-84.09%)
Mutual labels:  generative-adversarial-network
Exemplar-GAN-Eye-Inpainting-Tensorflow
Tensorflow implement of "Eye In-Painting with Exemplar Generative Adversarial Networks"
Stars: ✭ 98 (+11.36%)
Mutual labels:  generative-adversarial-network
tgan
The implementation of Temporal Generative Adversarial Nets with Singular Value Clipping
Stars: ✭ 70 (-20.45%)
Mutual labels:  generative-adversarial-network
Improved-Wasserstein-GAN-application-on-MRI-images
Improved Wasserstein GAN (WGAN-GP) application on medical (MRI) images
Stars: ✭ 23 (-73.86%)
Mutual labels:  generative-adversarial-network
View All Similar Projects ➔

VAEGAN

This is a code for generating images with VAEGAN (variational autoencoder + generative adversarial net). Its original code is [1]. Our implementation is done using Theano(>=0.8.0rc1).

Demonstoration

Download Labeled Faces in the Wild dataset, split it into train and test datasets, and train VAEGAN.

python get_lfw.py
python train.py configures/lfw.json

To monitor the progress of training, it morph face images reconstructed on the training dataset (Fig. 1) to randomly generated face images (Fig. 2).

Figure 1. Reconstructed images at the last epoch

Figure 2. Randomly generated images at the last epoch

Using the following command after training, we can make VAEGAN generate images that represent the morphing (Fig. 3) between randomly choosen two images from the test dataset (left and right end).

python morphing.py configures/lfw_morph.json

Figure 3. Morphing faces.

Optimization tips

  • The optimization procedure is composed of two phases. In early phase, we pretrain VAE using pixel-wise error and discriminator separately.
    In final phase, we train overall VAEGAN model as in [1].

  • We use the ADAM to train models in our example (eta=1e-3, beta1=0.9, beta2=0.999, epsilon=1e-8).

  • Depending on the probabilities of real/fake as real/fake on a minibatch at an each iteration, we change the cost that should be optimized as done in [2].

References

[1] https://github.com/andersbll/autoencoding_beyond_pixels
[2] https://github.com/skaae/vaeblog
[3] https://gist.github.com/Newmu/a56d5446416f5ad2bbac
[4] https://gist.github.com/kastnerkyle/f3f67424adda343fef40

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].