Creates a dynamic version of bidirectional recurrent neural network. (deprecated)
tf.compat.v1.nn.bidirectional_dynamic_rnn( cell_fw, cell_bw, inputs, sequence_length=None, initial_state_fw=None, initial_state_bw=None, dtype=None, parallel_iterations=None, swap_memory=False, time_major=False, scope=None )
Takes input and builds independent forward and backward RNNs. 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.
| ||An instance of RNNCell, to be used for forward direction.|
| ||An instance of RNNCell, to be used for backward direction.|
| || The RNN inputs. If time_major == False (default), this must be a tensor of shape: |
| || (optional) An int32/int64 vector, size |
| || (optional) An initial state for the forward RNN. This must be a tensor of appropriate type and shape |
| || (optional) Same as for |
| ||(optional) The data type for the initial states and expected output. Required if initial_states are not provided or RNN states have a heterogeneous dtype.|
| ||(Default: 32). The number of iterations to run in parallel. Those operations which do not have any temporal dependency and can be run in parallel, will be. This parameter trades off time for space. Values >> 1 use more memory but take less time, while smaller values use less memory but computations take longer.|
| ||Transparently swap the tensors produced in forward inference but needed for back prop from GPU to CPU. This allows training RNNs which would typically not fit on a single GPU, with very minimal (or no) performance penalty.|
| || The shape format of the |
| ||VariableScope for the created subgraph; defaults to "bidirectional_rnn"|
| A tuple (outputs, output_states) where: outputs: A tuple (output_fw, output_bw) containing the forward and the backward rnn output |
| || If |
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.