tf.nn.rnn_cell.ResidualWrapper

View source on GitHub

Class ResidualWrapper

RNNCell wrapper that ensures cell inputs are added to the outputs.

Aliases:

• Class tf.compat.v1.nn.rnn_cell.ResidualWrapper
• Class tf.contrib.rnn.ResidualWrapper

__init__

View source

__init__(
    *args,
    **kwargs
)

Constructs a ResidualWrapper for cell.

Args:

• cell: An instance of RNNCell.
• residual_fn: (Optional) The function to map raw cell inputs and raw cell outputs to the actual cell outputs of the residual network. Defaults to calling nest.map_structure on (lambda i, o: i + o), inputs and outputs.
• **kwargs: dict of keyword arguments for base layer.

Properties

graph

DEPRECATED FUNCTION

output_size

scope_name

state_size

Methods

tf.nn.rnn_cell.ResidualWrapper.get_initial_state

View source

get_initial_state(
    inputs=None,
    batch_size=None,
    dtype=None
)

tf.nn.rnn_cell.ResidualWrapper.zero_state

View source

zero_state(
    batch_size,
    dtype
)