Autoencoder¶

Implementation of a Vanilla Autoencoder model.

Available samplers¶

`NormalSampler`	Samples from a Standard normal distribution in the Autoencoder’s latent space.
`GaussianMixtureSampler`	Fits a Gaussian Mixture in the Autoencoder’s latent space.
`MAFSampler`	Fits a Masked Autoregressive Flow in the Autoencoder’s latent space.
`IAFSampler`	Fits an Inverse Autoregressive Flow in the Autoencoder’s latent space.

class pythae.models.AEConfig(input_dim=None, latent_dim=10, uses_default_encoder=True, uses_default_decoder=True)[source]¶

This is the autoencoder model configuration instance deriving from BaseAEConfig.

Parameters

class pythae.models.AE(model_config, encoder=None, decoder=None)[source]¶

Vanilla Autoencoder model.

Parameters

model_config (AEConfig) – The Autoencoder configuration setting the main parameters of the model.
encoder (BaseEncoder) – An instance of BaseEncoder (inheriting from torch.nn.Module which plays the role of encoder. This argument allows you to use your own neural networks architectures if desired. If None is provided, a simple Multi Layer Preception (https://en.wikipedia.org/wiki/Multilayer_perceptron) is used. Default: None.
decoder (BaseDecoder) – An instance of BaseDecoder (inheriting from torch.nn.Module which plays the role of decoder. This argument allows you to use your own neural networks architectures if desired. If None is provided, a simple Multi Layer Preception (https://en.wikipedia.org/wiki/Multilayer_perceptron) is used. Default: None.

Note

For high dimensional data we advice you to provide you own network architectures. With the provided MLP you may end up with a MemoryError.

forward(inputs, **kwargs)[source]¶

The input data is encoded and decoded