/autoencoders

implementations of various types of auto-encoders in tensorflow(in progress)

MIT LicenseMIT

Types of Autoencoders

  • [AE]: Fully-connected autoencoder
  • [SparseAE]: Sparse autoencoder
  • [DeepAE]: Deep (fully-connected) autoencoder
  • [ConvAE]: Convolutional autoencoder
  • [UpconvAE]: Upconvolutional autoencoder - also known by several other names
  • [DenoisingAE]: Denoising (convolutional) autoencoder
  • [CAE]: Contractive autoencoder
  • [Seq2SeqAE]: Sequence-to-sequence autoencoder
  • [VAE]: Variational autoencoder
  • [CatVAE]: Categorical variational autoencoder
  • [AAE]: Adversarial autoencoder
  • [WTA-AE]: Winner-take-all autoencoder

Variants of Variational Autoencoder

Name Paper Link Loss Function
VAE Arxiv
CVAE Arxiv
DVAE Arxiv (to be added)
AAE Arxiv (to be added)

Variants of VAE structure

References

Maintainer

Gopala KR / @gopala-kr