Similar to the unidirectional case above (rnn) but takes input and builds
independent forward and backward RNNs with the final forward and backward
outputs depth-concatenated, such that the output will have the format
[time][batch][cell_fw.output_size + cell_bw.output_size]. The input_size of
forward and backward cell must match. The initial state for both directions
is zero by default (but can be set optionally) and no intermediate states are
ever returned -- the network is fully unrolled for the given (passed in)
length(s) of the sequence(s) or completely unrolled if length(s) is not given.
Args
cell_fw
An instance of RNNCell, to be used for forward direction.
cell_bw
An instance of RNNCell, to be used for backward direction.
inputs
A length T list of inputs, each a tensor of shape [batch_size,
input_size], or a nested tuple of such elements.
initial_state_fw
(optional) An initial state for the forward RNN. This must
be a tensor of appropriate type and shape [batch_size,
cell_fw.state_size]. If cell_fw.state_size is a tuple, this should be a
tuple of tensors having shapes [batch_size, s] for s in
cell_fw.state_size.
initial_state_bw
(optional) Same as for initial_state_fw, but using the
corresponding properties of cell_bw.
dtype
(optional) The data type for the initial state. Required if either
of the initial states are not provided.
sequence_length
(optional) An int32/int64 vector, size [batch_size],
containing the actual lengths for each of the sequences.
scope
VariableScope for the created subgraph; defaults to
"bidirectional_rnn"
Returns
A tuple (outputs, output_state_fw, output_state_bw) where:
outputs is a length T list of outputs (one for each input), which
are depth-concatenated forward and backward outputs.
output_state_fw is the final state of the forward rnn.
output_state_bw is the final state of the backward rnn.
Raises
TypeError
If cell_fw or cell_bw is not an instance of RNNCell.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.nn.static_bidirectional_rnn\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/rnn.py#L1541-L1635) |\n\nCreates a bidirectional recurrent neural network. (deprecated)\n\n#### View aliases\n\n\n**Main aliases**\n\n\\`tf.contrib.rnn.static_bidirectional_rnn\\`\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.static_bidirectional_rnn`](/api_docs/python/tf/compat/v1/nn/static_bidirectional_rnn)\n\n\u003cbr /\u003e\n\n tf.nn.static_bidirectional_rnn(\n cell_fw, cell_bw, inputs, initial_state_fw=None, initial_state_bw=None,\n dtype=None, sequence_length=None, scope=None\n )\n\n| **Warning:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Please use `keras.layers.Bidirectional(keras.layers.RNN(cell, unroll=True))`, which is equivalent to this API\n\nSimilar to the unidirectional case above (rnn) but takes input and builds\nindependent forward and backward RNNs with the final forward and backward\noutputs depth-concatenated, such that the output will have the format\n\\[time\\]\\[batch\\]\\[cell_fw.output_size + cell_bw.output_size\\]. The input_size of\nforward and backward cell must match. The initial state for both directions\nis zero by default (but can be set optionally) and no intermediate states are\never returned -- the network is fully unrolled for the given (passed in)\nlength(s) of the sequence(s) or completely unrolled if length(s) is not given.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `cell_fw` | An instance of RNNCell, to be used for forward direction. |\n| `cell_bw` | An instance of RNNCell, to be used for backward direction. |\n| `inputs` | A length T list of inputs, each a tensor of shape \\[batch_size, input_size\\], or a nested tuple of such elements. |\n| `initial_state_fw` | (optional) An initial state for the forward RNN. This must be a tensor of appropriate type and shape `[batch_size, cell_fw.state_size]`. If `cell_fw.state_size` is a tuple, this should be a tuple of tensors having shapes `[batch_size, s] for s in cell_fw.state_size`. |\n| `initial_state_bw` | (optional) Same as for `initial_state_fw`, but using the corresponding properties of `cell_bw`. |\n| `dtype` | (optional) The data type for the initial state. Required if either of the initial states are not provided. |\n| `sequence_length` | (optional) An int32/int64 vector, size `[batch_size]`, containing the actual lengths for each of the sequences. |\n| `scope` | VariableScope for the created subgraph; defaults to \"bidirectional_rnn\" |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A tuple (outputs, output_state_fw, output_state_bw) where: outputs is a length `T` list of outputs (one for each input), which are depth-concatenated forward and backward outputs. output_state_fw is the final state of the forward rnn. output_state_bw is the final state of the backward rnn. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|------------------------------------------------------------|\n| `TypeError` | If `cell_fw` or `cell_bw` is not an instance of `RNNCell`. |\n| `ValueError` | If inputs is None or an empty list. |\n\n\u003cbr /\u003e"]]
View source on GitHub