Decoder

latent.modules.decoder.Decoder

Decoder base model. This model decompresses a latent space to reconstruct the input data by passing it through a DenseStack. It also takes care of adding the reconstruction loss to the model.

__init__(self, x_dim, name='decoder', hidden_units=[128, 128], reconstruction_loss=None, loss_name='rec_loss', initializer='glorot_normal', **kwargs) special

Parameters:

Name	Type	Description	Default
x_dim	int	Integer indicating the number of dimensions in the input data.	required
name	str	String indicating the name of the model.	'decoder'
hidden_units	Iterable[int]	Number of hidden units in DenseStack. If set to None the model skips the DenseStack and reduces to a linear decoder (Svensson 2020).	[128, 128]
reconstruction_loss	Union[Callable, str]	Function to compute reconstruction loss.	None
loss_name	str	String indicating the name of the loss.	'rec_loss'
initializer	Union[str, Callable]	Initializer for the kernel weights matrix (see keras.initializers)	'glorot_normal'
**kwargs		Other arguments passed on to DenseStack	{}