A collection of deep generative models, including the classic papers, their implementations in TensorFlow, tutorials, reviews, the most important conferences and workshops in related research areas.
Currently, these implementations are compatible with TensorFlow 1.4 or later. And this project is in progress.
- VAE: Auto-Encoding Variational Bayes (paper)
Stochastic Backpropagation and Approximate Inference in Deep Generative Models (paper) - GAN: Generative Adversarial Nets (paper)
- AVB: Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks (paper)
- Gumbel-SoftmaxVAE: Categorical Reparameterization with Gumbel-Softmax (paper)
The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables (paper) - VQVAE: Neural Discrete Representation Learning (paper)
- TripleGAN: Triple Generative Adversarial Nets (paper)
- ConditionalVAE: Semi-Supervised Learning with Deep Generative Models (paper)
- AAE: Adversarial Autoencoders (paper)
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization (paper)
- ImprovedGAN: Improved Techniques for Training GANs (paper)
- DCGAN: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (paper)
- WGAN: Wasserstein Generative Adversarial Networks (paper)
- AmbientGAN: Generative Models From Lossy Measurements (paper code)
- Progressive Growing of GANs for Improved Quality, Stability, and Variation (paper code)
- Wasserstein Auto-Encoders (paper)
- Spectral Normalization for Generative Adversarial Networks (paper)
- Kernel Implicit Variational Inference (paper)
- NIPS 2016 Tutorial: Generative Adversarial Networks (paper slides video)
- CVPR 2017 Tutorial: Theory and Application of Generative Adversarial Networks (slides video)
- Tutorial on Variational Autoencoders (paper)
- Bayesian Deep Learning and Generic Bayesian Inference (slides)