Tensorflow 2.0 implementation of generative models, e.g. VAE, GAN
- Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function (2019)
- An Introduction to Variational Autoencoders (2019)
- Tutorial on Variational Autoencoders (2016)
- Implementing Variational Autoencoders in Keras: Beyond the Quickstart Tutorial
- Gaussian mixture VAE: lessons in Variational Inference, Generative models, and Deep Nets
- Conditional convolutional auto-encoder, tensorflow code
- Auto-Encoding Variational Bayes (2013), keras code
- Conditional variational auto-encoder (CVAE) (2015), keras code, tensorflow code
- Adversarial autoencoders (2015), keras code, tensorflow code
- Sparse autoencoder (Andrew Ng), keras code
- Variational Auto Encoder with a Concrete latent distribution, The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables or Categorical Reparameterization with Gumbel-Softmax, keras code
- pytorch-generative-model-collections
- Generative Models Tutorial with Demo
- GauravBh1010tt/DL-Seq2Seq
- The implementation of the VAE and Gaussian Mixture VAE
- Unsupervised clustering with (Gaussian mixture) VAEs
Sequence
-
Generative models are also promising in the long term future because it has a potential power to learn the natural features of a dataset automatically.
-
Generative models are mostly used to generate images (vision area). In the recent studies, it will also used to generate sentences (natural language processing area).
Image
- Generative Adversarial Networks (2014)
- Conditional GANs (2014)
- DCGAN (2015)
- Improved Techniques for Training GANs (2016)
- Pix2Pix (2016)
- StackGAN (2016)
- CycleGAN (2017)
- Improved Training of Wasserstein GANs (2017)
- Progressively Growing GANs (2017)
- BigGAN (2018)
- StyleGAN (2018)
Sequence