tf.keras.layers.Bidirectional | TensorFlow v2.16.1 (original) (raw)

Bidirectional wrapper for RNNs.

tf.keras.layers.Bidirectional(
    layer,
    merge_mode='concat',
    weights=None,
    backward_layer=None,
    **kwargs
)

Used in the notebooks

Used in the tutorials
Text classification with an RNN Graph regularization for sentiment classification using synthesized graphs Neural machine translation with attention

Args
layer	keras.layers.RNN instance, such askeras.layers.LSTM or keras.layers.GRU. It could also be a keras.layers.Layer instance that meets the following criteria: Be a sequence-processing layer (accepts 3D+ inputs). Have a go_backwards, return_sequences and return_stateattribute (with the same semantics as for the RNN class). Have an input_spec attribute. Implement serialization via get_config() and from_config(). Note that the recommended way to create new RNN layers is to write a custom RNN cell and use it with keras.layers.RNN, instead of subclassing keras.layers.Layer directly. When return_sequences is True, the output of the masked timestep will be zero regardless of the layer's originalzero_output_for_mask value.
merge_mode	Mode by which outputs of the forward and backward RNNs will be combined. One of {"sum", "mul", "concat", "ave", None}. If None, the outputs will not be combined, they will be returned as a list. Defaults to "concat".
backward_layer	Optional keras.layers.RNN, or keras.layers.Layer instance to be used to handle backwards input processing. If backward_layer is not provided, the layer instance passed as the layer argument will be used to generate the backward layer automatically. Note that the provided backward_layer layer should have properties matching those of the layer argument, in particular it should have the same values for stateful, return_states,return_sequences, etc. In addition, backward_layerand layer should have different go_backwards argument values. A ValueError will be raised if these requirements are not met.

Call arguments
The call arguments for this layer are the same as those of the wrapped RNN layer. Beware that when passing the initial_stateargument during the call of this layer, the first half in the list of elements in the initial_state list will be passed to the forward RNN call and the last half in the list of elements will be passed to the backward RNN call.

Examples:

model = Sequential([
    Input(shape=(5, 10)),
    Bidirectional(LSTM(10, return_sequences=True),
    Bidirectional(LSTM(10)),
    Dense(5, activation="softmax"),
])
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

# With custom backward layer
forward_layer = LSTM(10, return_sequences=True)
backward_layer = LSTM(10, activation='relu', return_sequences=True,
                      go_backwards=True)
model = Sequential([
    Input(shape=(5, 10)),
    Bidirectional(forward_layer, backward_layer=backward_layer),
    Dense(5, activation="softmax"),
])
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

Attributes
input	Retrieves the input tensor(s) of a symbolic operation.Only returns the tensor(s) corresponding to the _first time_the operation was called.
output	Retrieves the output tensor(s) of a layer.Only returns the tensor(s) corresponding to the _first time_the operation was called.
states

Methods

`from_config`

View source

@classmethod from_config( config, custom_objects=None )

Creates a layer from its config.

This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).

Args
config	A Python dictionary, typically the output of get_config.

Returns
A layer instance.

`reset_state`

View source

reset_state()

`reset_states`

View source

reset_states()

`symbolic_call`

View source

symbolic_call(
    *args, **kwargs
)