# tf.keras.layers.Bidirectional

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/rnn/bidirectional.py#L36-L533) |

Bidirectional wrapper for RNNs.

Inherits From: [`Wrapper`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/Wrapper), [`Layer`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Module)

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

\`tf.compat.v1.keras.layers.Bidirectional\`

<br />

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

<br />

<br />

<br />

| ## Args ||
|---|---|
| `layer` | [`keras.layers.RNN`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/RNN) instance, such as [`keras.layers.LSTM`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/LSTM) or [`keras.layers.GRU`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/GRU). It could also be a [`keras.layers.Layer`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/Layer) instance that meets the following criteria: <br /> 1. Be a sequence-processing layer (accepts 3D+ inputs). 2. Have a `go_backwards`, `return_sequences` and `return_state` attribute (with the same semantics as for the `RNN` class). 3. Have an `input_spec` attribute. 4. 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`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/RNN), instead of subclassing [`keras.layers.Layer`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/Layer) directly. 5. When the `returns_sequences` is true, the output of the masked timestep will be zero regardless of the layer's original `zero_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. Default value is 'concat'. |
| `backward_layer` | Optional [`keras.layers.RNN`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/RNN), or [`keras.layers.Layer`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/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_layer` and `layer` should have different `go_backwards` argument values. A `ValueError` will be raised if these requirements are not met. |

<br />

<br />

<br />

| ## Call arguments ||
|---|---|
| The call arguments for this layer are the same as those of the wrapped RNN layer. Beware that when passing the `initial_state` argument 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. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | <br /> 1. If `layer` or `backward_layer` is not a `Layer` instance. 2. In case of invalid `merge_mode` argument. 3. If `backward_layer` has mismatched properties compared to `layer`. |

#### Examples:

    model = Sequential()
    model.add(Bidirectional(LSTM(10, return_sequences=True),
                                 input_shape=(5, 10)))
    model.add(Bidirectional(LSTM(10)))
    model.add(Dense(5))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

    # With custom backward layer
    model = Sequential()
    forward_layer = LSTM(10, return_sequences=True)
    backward_layer = LSTM(10, activation='relu', return_sequences=True,
                          go_backwards=True)
    model.add(Bidirectional(forward_layer, backward_layer=backward_layer,
                            input_shape=(5, 10)))
    model.add(Dense(5))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `constraints` | <br /> <br /> |

<br />

## Methods

### `reset_states`

[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/rnn/bidirectional.py#L449-L466)

    reset_states(
        states=None
    )