nalp.models.discriminators¶
Pre-defined discriminator architectures.
A package for already-implemented discriminator models.
- class nalp.models.discriminators.ConvDiscriminator(n_samplings: Optional[int] = 3, alpha: Optional[float] = 0.3, dropout_rate: Optional[float] = 0.3)¶
Bases:
nalp.core.Discriminator
A ConvDiscriminator class stands for the convolutional discriminative part of a Generative Adversarial Network.
- __init__(self, n_samplings: Optional[int] = 3, alpha: Optional[float] = 0.3, dropout_rate: Optional[float] = 0.3)¶
Initialization method.
- Parameters
n_samplings – Number of downsamplings to perform.
alpha – LeakyReLU activation threshold.
dropout_rate – Dropout activation rate.
- property alpha(self)¶
LeakyReLU activation threshold.
- call(self, x: tensorflow.Tensor, training: Optional[bool] = True)¶
Method that holds vital information whenever this class is called.
- Parameters
x – A tensorflow’s tensor holding input data.
training – Whether architecture is under training or not.
- Returns
The same tensor after passing through each defined layer.
- Return type
(tf.Tensor)
- class nalp.models.discriminators.EmbeddedTextDiscriminator(vocab_size: Optional[int] = 1, max_length: Optional[int] = 1, embedding_size: Optional[int] = 32, n_filters: Optional[Tuple[int, Ellipsis]] = 64, filters_size: Optional[Tuple[int, Ellipsis]] = 1, dropout_rate: Optional[float] = 0.25)¶
Bases:
nalp.core.Discriminator
A EmbeddedTextDiscriminator class stands for the text-discriminative part of a Generative Adversarial Network.
- __init__(self, vocab_size: Optional[int] = 1, max_length: Optional[int] = 1, embedding_size: Optional[int] = 32, n_filters: Optional[Tuple[int, Ellipsis]] = 64, filters_size: Optional[Tuple[int, Ellipsis]] = 1, dropout_rate: Optional[float] = 0.25)¶
Initialization method.
- Parameters
vocab_size – The size of the vocabulary.
max_length – Maximum length of the sequences.
embedding_size – The size of the embedding layer.
n_filters – Number of filters to be applied.
filters_size – Size of filters to be applied.
dropout_rate – Dropout activation rate.
- call(self, x: tensorflow.Tensor, training: Optional[bool] = True)¶
Method that holds vital information whenever this class is called.
- Parameters
x – A tensorflow’s tensor holding input data.
training – Whether architecture is under training or not.
- Returns
The same tensor after passing through each defined layer.
- Return type
(tf.Tensor)
- class nalp.models.discriminators.LSTMDiscriminator(embedding_size: Optional[int] = 32, hidden_size: Optional[int] = 64)¶
Bases:
nalp.core.Discriminator
A LSTMDiscriminator class is the one in charge of a discriminative Long Short-Term Memory implementation.
References
Hochreiter, Jürgen Schmidhuber. Long short-term memory. Neural computation 9.8 (1997).
- __init__(self, embedding_size: Optional[int] = 32, hidden_size: Optional[int] = 64)¶
Initialization method.
- Parameters
embedding_size – The size of the embedding layer.
hidden_size – The amount of hidden neurons.
- call(self, x: tensorflow.Tensor)¶
Method that holds vital information whenever this class is called.
- Parameters
x – A tensorflow’s tensor holding input data.
- Returns
The same tensor after passing through each defined layer.
- Return type
(tf.Tensor)
- class nalp.models.discriminators.LinearDiscriminator(n_samplings: Optional[int] = 3, alpha: Optional[float] = 0.01)¶
Bases:
nalp.core.Discriminator
A LinearDiscriminator class stands for the linear discriminative part of a Generative Adversarial Network.
- __init__(self, n_samplings: Optional[int] = 3, alpha: Optional[float] = 0.01)¶
Initialization method.
- Parameters
n_samplings – Number of downsamplings to perform.
alpha – LeakyReLU activation threshold.
- property alpha(self)¶
LeakyReLU activation threshold.
- call(self, x: tensorflow.Tensor, training: Optional[bool] = True)¶
Method that holds vital information whenever this class is called.
- Parameters
x – A tensorflow’s tensor holding input data.
training – Whether architecture is under training or not.
- Returns
The same tensor after passing through each defined layer.
- Return type
(tf.Tensor)
- class nalp.models.discriminators.TextDiscriminator(max_length: Optional[int] = 1, embedding_size: Optional[int] = 32, n_filters: Optional[Tuple[int, Ellipsis]] = 64, filters_size: Optional[Tuple[int, Ellipsis]] = 1, dropout_rate: Optional[float] = 0.25)¶
Bases:
nalp.core.Discriminator
A TextDiscriminator class stands for the text-discriminative part of a Generative Adversarial Network.
- __init__(self, max_length: Optional[int] = 1, embedding_size: Optional[int] = 32, n_filters: Optional[Tuple[int, Ellipsis]] = 64, filters_size: Optional[Tuple[int, Ellipsis]] = 1, dropout_rate: Optional[float] = 0.25)¶
Initialization method.
- Parameters
max_length – Maximum length of the sequences.
embedding_size – The size of the embedding layer.
n_filters – Number of filters to be applied.
filters_size – Size of filters to be applied.
dropout_rate – Dropout activation rate.
- call(self, x: tensorflow.Tensor, training: Optional[bool] = True)¶
Method that holds vital information whenever this class is called.
- Parameters
x – A tensorflow’s tensor holding input data.
training – Whether architecture is under training or not.
- Returns
The same tensor after passing through each defined layer.
- Return type
(tf.Tensor)