encoders

Collection of Encoders (i.e., GANs’ Discriminators) models.

Classes

BaseEncoder

Primitive Model for all fully connected encoder based architecture.

class ashpy.models.fc.encoders.BaseEncoder(hidden_units, output_shape)

Bases: ashpy.models.fc.interfaces.FCInterface

Primitive Model for all fully connected encoder based architecture.

Examples

encoder = BaseEncoder(
    hidden_units=[256,128,64],
    output_shape=10)
print(encoder(tf.zeros((1,55))).shape)

(1, 10)

__init__(hidden_units, output_shape)

Instantiate the BaseDecoder.

Parameters

• hidden_units (tuple of int) – Number of units per hidden layer.

• output_shape (int) – Amount of units of the last tf.keras.layers.Dense.

Returns

None