GRUCellMML

class keras_mml.layers.recurrent.GRUCellMML

Cell class for the GRUMML layer.

This class processes one step within the whole time sequence input, whereas GRUMML processes the whole sequence.

units

Dimensionality of the output space.

fully_mml

Whether to use matmul-free operations for all the layers.

num_heads

Number of heads to use when performing the recurrent step.

activation

Activation function to use.

recurrent_activation

Activation function to use for the recurrent step.

use_bias

Whether to use a bias vector for the layer.

weights_initializer

Initializer for the gates’ matrices. Used for the linear transformation of the inputs.

bias_initializer

Initializer for the bias vector.

weights_regularizer

Regularizer function applied to the gates’ matrices.

bias_regularizer

Regularizer function applied to the bias vector.

weights_constraint

Constraint function applied to the gates’ matrices.

bias_constraint

Constraint function applied to the bias vector.

state_size

Size of the recurrent state.

output_size

Size of the output vector.

__init__(units, fully_mml=False, num_heads=1, activation='silu', recurrent_activation='sigmoid', use_bias=True, weights_initializer='glorot_uniform', bias_initializer='zeros', weights_regularizer=None, bias_regularizer=None, weights_constraint=None, bias_constraint=None, **kwargs)

Initializes a new instance of the layer.

Parameters:

• units (int) – Dimensionality of the output space.

• fully_mml (bool, default: False) – Whether to use matmul-free operations for all the layers.

• num_heads (int, default: 1) – Number of heads to use when performing the recurrent step.

• activation (str, default: 'silu') – Activation function to use.

• recurrent_activation (str, default: 'sigmoid') – Activation function to use for the recurrent step.

• use_bias (bool, default: True) – Whether to use a bias vector for the layer.

• weights_initializer (str, default: 'glorot_uniform') – Initializer for the gates’ matrices. Used for the linear transformation of the inputs.

• bias_initializer (str, default: 'zeros') – Initializer for the bias vector.

• weights_regularizer (Optional[str], default: None) – Regularizer function applied to the gates’ matrices.

• bias_regularizer (Optional[str], default: None) – Regularizer function applied to the bias vector.

• weights_constraint (Optional[str], default: None) – Constraint function applied to the gates’ matrices.

• bias_constraint (Optional[str], default: None) – Constraint function applied to the bias vector.

• **kwargs – Keyword arguments for keras.Layer.

Raises:

• ValueError – If the units provided is not a positive integer.

• ValueError – If the number of heads to use is not a positive integer.

• ValueError – If the number of heads does not divide the units provided.

build(input_shape)

Create layer weights.

Parameters:

input_shape (Tuple[int, int]) – Shape of the input.

call(inputs, states, training=False)

Calling method of the cell.

Parameters:

• inputs (Float[ndarray, 'batch_size features']) – Inputs into the layer.

• states (Float[ndarray, '*state_dims']) – State(s) from the previous timestep.

• training (default: False) – Whether the layer should behave in training mode or in inference mode.

Returns:

Float[ndarray, 'batch_size units'] – Transformed inputs.

get_config()

Gets the configuration for the layer.

Returns:

Layer configuration.

get_initial_state(batch_size=None)

Gets the initial states.

Parameters:

batch_size (Optional[int], default: None) – Batch size for the cell.

Returns:

List[ndarray] – Initial states.