Autoencoder

Inheritance Diagram

Inheritance diagram of ashpy.models.fc.autoencoders.Autoencoder

class ashpy.models.fc.autoencoders.Autoencoder(hidden_units, encoding_dimension, output_shape)[source]

Bases: tensorflow.python.keras.engine.training.Model

Primitive Model for all fully connected autoencoders.

Examples

  • Direct Usage:
    autoencoder = Autoencoder(
        hidden_units=[256,128,64],
        encoding_dimension=100,
        output_shape=55
    )
    
    encoding, reconstruction = autoencoder(tf.zeros((1, 55)))
    print(encoding.shape)
    print(reconstruction.shape)
    
    
    

Methods

__init__(hidden_units, encoding_dimension, …) Instantiate the Decoder.
call(inputs[, training]) Execute the model on input data.

Attributes

activity_regularizer Optional regularizer function for the output of this layer.
dtype
dynamic
inbound_nodes Deprecated, do NOT use! Only for compatibility with external Keras.
input Retrieves the input tensor(s) of a layer.
input_mask Retrieves the input mask tensor(s) of a layer.
input_shape Retrieves the input shape(s) of a layer.
input_spec Gets the network’s input specs.
layers
losses Losses which are associated with this Layer.
metrics Returns the model’s metrics added using compile, add_metric APIs.
metrics_names Returns the model’s display labels for all outputs.
name Returns the name of this module as passed or determined in the ctor.
name_scope Returns a tf.name_scope instance for this class.
non_trainable_variables
non_trainable_weights
outbound_nodes Deprecated, do NOT use! Only for compatibility with external Keras.
output Retrieves the output tensor(s) of a layer.
output_mask Retrieves the output mask tensor(s) of a layer.
output_shape Retrieves the output shape(s) of a layer.
run_eagerly Settable attribute indicating whether the model should run eagerly.
sample_weights
state_updates Returns the updates from all layers that are stateful.
stateful
submodules Sequence of all sub-modules.
trainable
trainable_variables Sequence of variables owned by this module and it’s submodules.
trainable_weights
updates
variables Returns the list of all layer variables/weights.
weights Returns the list of all layer variables/weights.
__init__(hidden_units, encoding_dimension, output_shape)[source]

Instantiate the Decoder.

Parameters:
  • hidden_units (tuple of int) – Number of units per hidden layer.
  • encoding_dimension (int) – encoding dimension.
  • output_shape (int) – output shape, usual equal to the input shape.
Returns:

None

call(inputs, training=True)[source]

Execute the model on input data.

Parameters:
  • inputs (tf.Tensor) – Input tensors.
  • training (bool) – Training flag.
Returns:

(encoding, reconstruction) – Pair of tensors.