fusionlab.nn.components.GatedResidualNetwork

class fusionlab.nn.components.GatedResidualNetwork

Bases: Layer

Gated Residual Network applying transformations with optional context.

__init__(units, dropout_rate=0.0, activation='elu', output_activation=None, use_batch_norm=False, use_time_distributed=None, **kwargs)

Initializes the GatedResidualNetwork layer.

Parameters:

• units (int)

• dropout_rate (float)

• activation (str)

• output_activation (str | None)

• use_batch_norm (bool)

• use_time_distributed (bool | None)

Methods

__init__(units[, dropout_rate, activation, ...])	Initializes the GatedResidualNetwork layer.
add_loss(loss)	Can be called inside of the call() method to add a scalar loss.
add_metric(*args, **kwargs)
add_variable(shape, initializer[, dtype, ...])	Add a weight variable to the layer.
add_weight([shape, initializer, dtype, ...])	Add a weight variable to the layer.
build(input_shape)	Builds the residual projection layer if needed.
build_from_config(config)	Builds the layer's states with the supplied config dict.
call(x[, context, training])	Forward pass implementing GRN with optional context.
compute_mask(inputs, previous_mask)
compute_output_shape(*args, **kwargs)
compute_output_spec(*args, **kwargs)
count_params()	Count the total number of scalars composing the weights.
from_config(config)	Creates layer from its config.
get_build_config()	Returns a dictionary with the layer's input shape.
get_config()	Returns the layer configuration.
get_weights()	Return the values of layer.weights as a list of NumPy arrays.
load_own_variables(store)	Loads the state of the layer.
quantize(mode[, type_check, config])
quantized_build(input_shape, mode)
quantized_call(*args, **kwargs)
rematerialized_call(layer_call, *args, **kwargs)	Enable rematerialization dynamically for layer's call method.
save_own_variables(store)	Saves the state of the layer.
set_weights(weights)	Sets the values of layer.weights from a list of NumPy arrays.
stateless_call(trainable_variables, ...[, ...])	Call the layer without any side effects.
symbolic_call(*args, **kwargs)

Attributes

compute_dtype	The dtype of the computations performed by the layer.
dtype	Alias of layer.variable_dtype.
dtype_policy
input	Retrieves the input tensor(s) of a symbolic operation.
input_dtype	The dtype layer inputs should be converted to.
input_spec
losses	List of scalar losses from add_loss, regularizers and sublayers.
metrics	List of all metrics.
metrics_variables	List of all metric variables.
non_trainable_variables	List of all non-trainable layer state.
non_trainable_weights	List of all non-trainable weight variables of the layer.
output	Retrieves the output tensor(s) of a layer.
path	The path of the layer.
quantization_mode	The quantization mode of this layer, None if not quantized.
supports_masking	Whether this layer supports computing a mask using compute_mask.
trainable	Settable boolean, whether this layer should be trainable or not.
trainable_variables	List of all trainable layer state.
trainable_weights	List of all trainable weight variables of the layer.
variable_dtype	The dtype of the state (weights) of the layer.
variables	List of all layer state, including random seeds.
weights	List of all weight variables of the layer.

__init__(units, dropout_rate=0.0, activation='elu', output_activation=None, use_batch_norm=False, use_time_distributed=None, **kwargs)

Initializes the GatedResidualNetwork layer.

Parameters:

• units (int)

• dropout_rate (float)

• activation (str)

• output_activation (str | None)

• use_batch_norm (bool)

• use_time_distributed (bool | None)

build(input_shape)

Builds the residual projection layer if needed.

call(x, context=None, training=False)

Forward pass implementing GRN with optional context.

get_config()

Returns the layer configuration.

classmethod from_config(config)

Creates layer from its config.