DisentangledBetaVAE¶
This module is the implementation of the Disentangled Beta VAE proposed in (https://arxiv.org/abs/1804.03599). This model adds a new parameter to the \(\beta\)-VAE loss function corresponding to the target value for the KL between the prior and the posterior distribution. It is progressively increased throughout training.
Available samplers¶
Samples from a Standard normal distribution in the Autoencoder’s latent space. |
|
Fits a Gaussian Mixture in the Autoencoder’s latent space. |
|
Fits a second VAE in the Autoencoder’s latent space. |
|
Fits a Masked Autoregressive Flow in the Autoencoder’s latent space. |
|
Fits an Inverse Autoregressive Flow in the Autoencoder’s latent space. |
- class pythae.models.DisentangledBetaVAEConfig(input_dim=None, latent_dim=10, uses_default_encoder=True, uses_default_decoder=True, reconstruction_loss='mse', beta=10.0, C=50.0, warmup_epoch=25)[source]¶
Disentangled \(\beta\)-VAE model config config class
- Parameters
input_dim (tuple) – The input_data dimension.
latent_dim (int) – The latent space dimension. Default: None.
reconstruction_loss (str) – The reconstruction loss to use [‘bce’, ‘mse’]. Default: ‘mse’
beta (float) – The balancing factor. Default: 10.
C (float) – The value of the KL divergence term of the ELBO we wish to approach, measured in nats. Default: 50.
warmup_epoch (int) – The number of epochs during which the KL divergence objective will increase from 0 to C (should be smaller or equal to nb_epochs). Default: 100
epoch (int) – The current epoch. Default: 0
- class pythae.models.DisentangledBetaVAE(model_config, encoder=None, decoder=None)[source]¶
Disentangled \(\beta\)-VAE model.
- Parameters
model_config (DisentangledBetaVAEConfig) – The Variational 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.