A length T list of inputs, each a Tensor of shape [batch_size,
input_size].
state_saver
A state saver object with methods state and save_state.
state_name
Python string or tuple of strings. The name to use with the
state_saver. If the cell returns tuples of states (i.e., cell.state_size
is a tuple) then state_name should be a tuple of strings having the same
length as cell.state_size. Otherwise it should be a single string.
sequence_length
(optional) An int32/int64 vector size [batch_size]. See the
documentation for rnn() for more details about sequence_length.
scope
VariableScope for the created subgraph; defaults to "rnn".
Returns
A pair (outputs, state) where:
outputs is a length T list of outputs (one for each input)
states is the final state
Raises
TypeError
If cell is not an instance of RNNCell.
ValueError
If inputs is None or an empty list, or if the arity and
type of state_name does not match that of cell.state_size.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tf.compat.v1.nn.static_state_saving_rnn\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/ops/rnn.py#L1491-L1586) |\n\nRNN that accepts a state saver for time-truncated RNN calculation. (deprecated) \n\n tf.compat.v1.nn.static_state_saving_rnn(\n cell, inputs, state_saver, state_name, sequence_length=None, scope=None\n )\n\n| **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Please use [`keras.layers.RNN(cell, stateful=True)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RNN), which is equivalent to this API\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `cell` | An instance of `RNNCell`. |\n| `inputs` | A length T list of inputs, each a `Tensor` of shape `[batch_size, input_size]`. |\n| `state_saver` | A state saver object with methods `state` and `save_state`. |\n| `state_name` | Python string or tuple of strings. The name to use with the state_saver. If the cell returns tuples of states (i.e., `cell.state_size` is a tuple) then `state_name` should be a tuple of strings having the same length as `cell.state_size`. Otherwise it should be a single string. |\n| `sequence_length` | (optional) An int32/int64 vector size \\[batch_size\\]. See the documentation for rnn() for more details about sequence_length. |\n| `scope` | VariableScope for the created subgraph; defaults to \"rnn\". |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A pair (outputs, state) where: outputs is a length T list of outputs (one for each input) states is the final state ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|----------------------------------------------------------------------------------------------------------------------------|\n| `TypeError` | If `cell` is not an instance of RNNCell. |\n| `ValueError` | If `inputs` is `None` or an empty list, or if the arity and type of `state_name` does not match that of `cell.state_size`. |\n\n\u003cbr /\u003e"]]
View source on GitHub