Every RNNCell must have the properties below and implement call with
the signature (output, next_state) = call(input, state). The optional
third input argument, scope, is allowed for backwards compatibility
purposes; but should be left off for new subclasses.
This definition of cell differs from the definition used in the literature.
In the literature, 'cell' refers to an object with a single scalar output.
This definition refers to a horizontal array of such units.
An RNN cell, in the most abstract setting, is anything that has
a state and performs some operation that takes a matrix of inputs.
This operation results in an output matrix with self.output_size columns.
If self.state_size is an integer, this operation also results in a new
state matrix with self.state_size columns. If self.state_size is a
(possibly nested tuple of) TensorShape object(s), then it should return a
matching structure of Tensors having shape [batch_size].concatenate(s)
for each s in self.batch_size.
Attributes
graph
DEPRECATED FUNCTION
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.
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.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.nn.rnn_cell.RNNCell\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/rnn_cell_impl.py#L183-L344) |\n\nAbstract object representing an RNN cell.\n\nInherits From: [`Layer`](../../../tf/layers/Layer)\n\n#### View aliases\n\n\n**Main aliases**\n\n\\`tf.contrib.rnn.RNNCell\\`\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.nn.rnn_cell.RNNCell`](/api_docs/python/tf/compat/v1/nn/rnn_cell/RNNCell)\n\n\u003cbr /\u003e\n\n tf.nn.rnn_cell.RNNCell(\n trainable=True, name=None, dtype=None, **kwargs\n )\n\nEvery `RNNCell` must have the properties below and implement `call` with\nthe signature `(output, next_state) = call(input, state)`. The optional\nthird input argument, `scope`, is allowed for backwards compatibility\npurposes; but should be left off for new subclasses.\n\nThis definition of cell differs from the definition used in the literature.\nIn the literature, 'cell' refers to an object with a single scalar output.\nThis definition refers to a horizontal array of such units.\n\nAn RNN cell, in the most abstract setting, is anything that has\na state and performs some operation that takes a matrix of inputs.\nThis operation results in an output matrix with `self.output_size` columns.\nIf `self.state_size` is an integer, this operation also results in a new\nstate matrix with `self.state_size` columns. If `self.state_size` is a\n(possibly nested tuple of) TensorShape object(s), then it should return a\nmatching structure of Tensors having shape `[batch_size].concatenate(s)`\nfor each `s` in `self.batch_size`.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|---------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `graph` | DEPRECATED FUNCTION \u003cbr /\u003e | **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. |\n| `output_size` | Integer or TensorShape: size of outputs produced by this cell. |\n| `scope_name` | \u003cbr /\u003e |\n| `state_size` | size(s) of state(s) used by this cell. \u003cbr /\u003e It can be represented by an Integer, a TensorShape or a tuple of Integers or TensorShapes. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `get_initial_state`\n\n[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/rnn_cell_impl.py#L281-L309) \n\n get_initial_state(\n inputs=None, batch_size=None, dtype=None\n )\n\n### `zero_state`\n\n[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/rnn_cell_impl.py#L311-L340) \n\n zero_state(\n batch_size, dtype\n )\n\nReturn zero-filled state tensor(s).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|--------------|---------------------------------------------------------|\n| `batch_size` | int, float, or unit Tensor representing the batch size. |\n| `dtype` | the data type to use for the state. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| 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. \u003cbr /\u003e 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`. ||\n\n\u003cbr /\u003e"]]
View source on GitHub