# tf.compat.v1.nn.rnn_cell.LSTMCell
|---| | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.14.0/keras/layers/rnn/legacy_cells.py#L857-L1183) | Long short-term memory unit (LSTM) recurrent network cell. Inherits From: [`RNNCell`](https://www.tensorflow.org/versions/r2.14/api_docs/python/tf/compat/v1/nn/rnn_cell/RNNCell), [`Layer`](https://www.tensorflow.org/versions/r2.14/api_docs/python/tf/compat/v1/layers/Layer), [`Layer`](https://www.tensorflow.org/versions/r2.14/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.14/api_docs/python/tf/Module) tf.compat.v1.nn.rnn_cell.LSTMCell( num_units, use_peepholes=False, cell_clip=None, initializer=None, num_proj=None, proj_clip=None, num_unit_shards=None, num_proj_shards=None, forget_bias=1.0, state_is_tuple=True, activation=None, reuse=None, name=None, dtype=None, **kwargs ) The default non-peephole implementation is based on (Gers et al., 1999). The peephole implementation is based on (Sak et al., 2014). The class uses optional peep-hole connections, optional cell clipping, and an optional projection layer. Note that this cell is not optimized for performance. Please use `tf.compat.v1.keras.layers.CuDNNLSTM` for better performance on GPU, or [`tf.raw_ops.LSTMBlockCell`](https://www.tensorflow.org/versions/r2.14/api_docs/python/tf/raw_ops/LSTMBlockCell) for better performance on CPU. References: Long short-term memory recurrent neural network architectures for large scale acoustic modeling: [Sak et al., 2014](https://www.isca-speech.org/archive/interspeech_2014/i14_0338.html) ([pdf](https://www.isca-speech.org/archive/archive_papers/interspeech_2014/i14_0338.pdf)) Learning to forget: [Gers et al., 1999](http://digital-library.theiet.org/content/conferences/10.1049/cp_19991218) ([pdf](https://arxiv.org/pdf/1409.2329.pdf)) Long Short-Term Memory: [Hochreiter et al., 1997](https://www.mitpressjournals.org/doi/abs/10.1162/neco.1997.9.8.1735) ([pdf](http://ml.jku.at/publications/older/3504.pdf))


| ## Args || |---|---| | `num_units` | int, The number of units in the LSTM cell. | | `use_peepholes` | bool, set True to enable diagonal/peephole connections. | | `cell_clip` | (optional) A float value, if provided the cell state is clipped by this value prior to the cell output activation. | | `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` | Deprecated, will be removed by Jan. 2017. Use a variable_scope partitioner instead. | | `num_proj_shards` | Deprecated, will be removed by Jan. 2017. Use a variable_scope partitioner instead. | | `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. Must set it manually to `0.0` when restoring from CudnnLSTM trained checkpoints. | | `state_is_tuple` | If True, accepted and returned states are 2-tuples of the `c_state` and `m_state`. If False, they are concatenated along the column axis. This latter behavior will soon be deprecated. | | `activation` | Activation function of the inner states. Default: `tanh`. It could also be string that is within Keras activation function names. | | `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. | | `name` | String, the name of the layer. Layers with the same name will share weights, but to avoid mistakes we require reuse=True in such cases. | | `dtype` | Default dtype of the layer (default of `None` means use the type of the first input). Required when `build` is called before `call`. | | `**kwargs` | Dict, keyword named properties for common layer attributes, like `trainable` etc when constructing the cell from configs of get_config(). When restoring from CudnnLSTM-trained checkpoints, use `CudnnCompatibleLSTMCell` instead. |



| ## Attributes || |---|---| | `graph` |

| | `output_size` | Integer or TensorShape: size of outputs produced by this cell. | | `scope_name` |

| | `state_size` | size(s) of state(s) used by this cell.
It can be represented by an Integer, a TensorShape or a tuple of Integers or TensorShapes. |
## Methods ### `apply` [View source](https://github.com/keras-team/keras/tree/v2.14.0/keras/legacy_tf_layers/base.py#L239-L240) apply( *args, **kwargs ) ### `get_initial_state` [View source](https://github.com/keras-team/keras/tree/v2.14.0/keras/layers/rnn/legacy_cells.py#L254-L290) get_initial_state( inputs=None, batch_size=None, dtype=None ) ### `get_losses_for` [View source](https://github.com/keras-team/keras/tree/v2.14.0/keras/engine/base_layer_v1.py#L1467-L1484) get_losses_for( inputs ) Retrieves losses relevant to a specific set of inputs.


| Args || |---|---| | `inputs` | Input tensor or list/tuple of input tensors. |



| Returns || |---|---| | List of loss tensors of the layer that depend on `inputs`. ||
### `get_updates_for` [View source](https://github.com/keras-team/keras/tree/v2.14.0/keras/engine/base_layer_v1.py#L1448-L1465) get_updates_for( inputs ) Retrieves updates relevant to a specific set of inputs.


| Args || |---|---| | `inputs` | Input tensor or list/tuple of input tensors. |



| Returns || |---|---| | List of update ops of the layer that depend on `inputs`. ||
### `zero_state` [View source](https://github.com/keras-team/keras/tree/v2.14.0/keras/layers/rnn/legacy_cells.py#L292-L328) zero_state( batch_size, dtype ) Return zero-filled state tensor(s).


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



| 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.
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`. ||