LayerWrapper

class opennmt.layers.LayerWrapper(*args, **kwargs)

Layer wrapper for input/output normalization, input/output dropout and residual connection.

Inherits from: keras.src.engine.base_layer.Layer

Extended by:

• opennmt.layers.RNNCellWrapper

• opennmt.layers.TransformerLayerWrapper

__init__(layer, normalize_input=False, normalize_output=False, input_dropout=0, output_dropout=0, residual_connection=False, **kwargs)

Initializes the layer.

Parameters

• layer – The layer to wrap.

• normalize_input – Apply layer normalization on the input.

• normalize_output – Apply layer normalization on the output.

• input_dropout – The probability to drop units in the layer input.

• output_dropout – The probability to drop units in the layer output.

• residual_connection – Add the inputs to layer outputs (if their shape are compatible).

• kwargs – Additional layer arguments.

call(inputs, *args, **kwargs)

Runs the wrapper.

get_config()

Returns the layer wrapper configuration.

classmethod from_config(config)

Creates a layer wrapper from its configuration.