# tf.keras.layers.StackedRNNCells

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/keras/layers/StackedRNNCells) | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/layers/recurrent.py#L49-L179) |

Wrapper allowing a stack of RNN cells to behave as a single cell.

Inherits From: [`Layer`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/keras/layers/Layer)

#### View aliases


**Compat aliases for migration**

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

[`tf.compat.v1.keras.layers.StackedRNNCells`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/StackedRNNCells), \`tf.compat.v2.keras.layers.StackedRNNCells\`

<br />

    tf.keras.layers.StackedRNNCells(
        cells, **kwargs
    )

Used to implement efficient stacked RNNs.

<br />

<br />

<br />

| ## Arguments ||
|---|---|
| `cells` | List of RNN cell instances. |

<br />

#### Examples:

    cells = [
        keras.layers.LSTMCell(output_dim),
        keras.layers.LSTMCell(output_dim),
        keras.layers.LSTMCell(output_dim),
    ]

    inputs = keras.Input((timesteps, input_dim))
    x = keras.layers.RNN(cells)(inputs)

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `output_size` | <br /> <br /> |
| `state_size` | <br /> <br /> |

<br />

## Methods

### `get_initial_state`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/layers/recurrent.py#L107-L118)

    get_initial_state(
        inputs=None, batch_size=None, dtype=None
    )