# tf.contrib.rnn.CoupledInputForgetGateLSTMCell

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/rnn/python/ops/rnn_cell.py#L98-L322) |

Long short-term memory unit (LSTM) recurrent network cell.

Inherits From: [`RNNCell`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/nn/rnn_cell/RNNCell)

    tf.contrib.rnn.CoupledInputForgetGateLSTMCell(
        num_units, use_peepholes=False, initializer=None, num_proj=None, proj_clip=None,
        num_unit_shards=1, num_proj_shards=1, forget_bias=1.0, state_is_tuple=True,
        activation=tf.math.tanh, reuse=None, layer_norm=False, norm_gain=1.0,
        norm_shift=0.0
    )

The default non-peephole implementation is based on:

<https://pdfs.semanticscholar.org/1154/0131eae85b2e11d53df7f1360eeb6476e7f4.pdf>

Felix Gers, Jurgen Schmidhuber, and Fred Cummins.
"Learning to forget: Continual prediction with LSTM." IET, 850-855, 1999.

The peephole implementation is based on:

<https://research.google.com/pubs/archive/43905.pdf>

Hasim Sak, Andrew Senior, and Francoise Beaufays.
"Long short-term memory recurrent neural network architectures for
large scale acoustic modeling." INTERSPEECH, 2014.

The coupling of input and forget gate is based on:

<http://arxiv.org/pdf/1503.04069.pdf>

Greff et al. "LSTM: A Search Space Odyssey"

The class uses optional peep-hole connections, and an optional projection
layer.
Layer normalization implementation is based on:

<https://arxiv.org/abs/1607.06450>

"Layer Normalization"
Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton

and is applied before the internal nonlinearities.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `num_units` | int, The number of units in the LSTM cell |
| `use_peepholes` | bool, set True to enable diagonal/peephole connections. |
| `initializer` | (optional) The initializer to use for the weight and projection matrices. |
| `num_proj` | (optional) int, The output dimensionality for the projection matrices. If None, no projection is performed. |
| `proj_clip` | (optional) A float value. If `num_proj > 0` and `proj_clip` is provided, then the projected values are clipped elementwise to within `[-proj_clip, proj_clip]`. |
| `num_unit_shards` | How to split the weight matrix. If \>1, the weight matrix is stored across num_unit_shards. |
| `num_proj_shards` | How to split the projection matrix. If \>1, the projection matrix is stored across num_proj_shards. |
| `forget_bias` | Biases of the forget gate are initialized by default to 1 in order to reduce the scale of forgetting at the beginning of the training. |
| `state_is_tuple` | If True, accepted and returned states are 2-tuples of the `c_state` and `m_state`. By default (False), they are concatenated along the column axis. This default behavior will soon be deprecated. |
| `activation` | Activation function of the inner states. |
| `reuse` | (optional) Python boolean describing whether to reuse variables in an existing scope. If not `True`, and the existing scope already has the given variables, an error is raised. |
| `layer_norm` | If `True`, layer normalization will be applied. |
| `norm_gain` | float, The layer normalization gain initial value. If `layer_norm` has been set to `False`, this argument will be ignored. |
| `norm_shift` | float, The layer normalization shift initial value. If `layer_norm` has been set to `False`, this argument will be ignored. |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `graph` | DEPRECATED FUNCTION <br /> > [!WARNING] > **Warning:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Stop using this property because tf.layers layers no longer track their graph. |
| `output_size` | Integer or TensorShape: size of outputs produced by this cell. |
| `scope_name` | <br /> |
| `state_size` | size(s) of state(s) used by this cell. <br /> It can be represented by an Integer, a TensorShape or a tuple of Integers or TensorShapes. |

<br />

## Methods

### `get_initial_state`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/rnn_cell_impl.py#L281-L309)

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

### `zero_state`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/rnn_cell_impl.py#L311-L340)

    zero_state(
        batch_size, dtype
    )

Return zero-filled state tensor(s).

<br />

<br />

<br />

| Args ||
|---|---|
| `batch_size` | int, float, or unit Tensor representing the batch size. |
| `dtype` | the data type to use for the state. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| If `state_size` is an int or TensorShape, then the return value is a `N-D` tensor of shape `[batch_size, state_size]` filled with zeros. <br /> If `state_size` is a nested list or tuple, then the return value is a nested list or tuple (of the same structure) of `2-D` tensors with the shapes `[batch_size, s]` for each s in `state_size`. ||

<br />