tf.compat.v1.nn.rnn_cell.RNNCell
Stay organized with collections
Save and categorize content based on your preferences.
Abstract object representing an RNN cell.
Inherits From: Layer, Layer, Module
tf.compat.v1.nn.rnn_cell.RNNCell(
trainable=True, name=None, dtype=None, **kwargs
)
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
|
|
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
apply(
*args, **kwargs
)
get_initial_state
View source
get_initial_state(
inputs=None, batch_size=None, dtype=None
)
get_losses_for
View source
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
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
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.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2023-10-06 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2023-10-06 UTC."],[],[],null,["# tf.compat.v1.nn.rnn_cell.RNNCell\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/rnn/legacy_cells.py#L147-L338) |\n\nAbstract object representing an RNN cell.\n\nInherits From: [`Layer`](../../../../../tf/compat/v1/layers/Layer), [`Layer`](../../../../../tf/keras/layers/Layer), [`Module`](../../../../../tf/Module) \n\n tf.compat.v1.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` | \u003cbr /\u003e \u003cbr /\u003e |\n| `output_size` | Integer or TensorShape: size of outputs produced by this cell. |\n| `scope_name` | \u003cbr /\u003e \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### `apply`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/legacy_tf_layers/base.py#L239-L240) \n\n apply(\n *args, **kwargs\n )\n\n### `get_initial_state`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/rnn/legacy_cells.py#L254-L290) \n\n get_initial_state(\n inputs=None, batch_size=None, dtype=None\n )\n\n### `get_losses_for`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/engine/base_layer_v1.py#L1467-L1484) \n\n get_losses_for(\n inputs\n )\n\nRetrieves losses relevant to a specific set of inputs.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|----------|----------------------------------------------|\n| `inputs` | Input tensor or list/tuple of input tensors. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| List of loss tensors of the layer that depend on `inputs`. ||\n\n\u003cbr /\u003e\n\n### `get_updates_for`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/engine/base_layer_v1.py#L1448-L1465) \n\n get_updates_for(\n inputs\n )\n\nRetrieves updates relevant to a specific set of inputs.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|----------|----------------------------------------------|\n| `inputs` | Input tensor or list/tuple of input tensors. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| List of update ops of the layer that depend on `inputs`. ||\n\n\u003cbr /\u003e\n\n### `zero_state`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/rnn/legacy_cells.py#L292-L328) \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