Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tf.contrib.rnn.HighwayWrapper

View source on GitHub

Class HighwayWrapper

RNNCell wrapper that adds highway connection on cell input and output.

Inherits From: RNNCell

Based on:

R. K. Srivastava, K. Greff, and J. Schmidhuber, "Highway networks", arXiv preprint arXiv:1505.00387, 2015. https://arxiv.org/abs/1505.00387

__init__

View source

__init__(
    cell,
    couple_carry_transform_gates=True,
    carry_bias_init=1.0
)

Constructs a HighwayWrapper for cell.

Args:

  • cell: An instance of RNNCell.
  • couple_carry_transform_gates: boolean, should the Carry and Transform gate be coupled.
  • carry_bias_init: float, carry gates bias initialization.

Properties

graph

DEPRECATED FUNCTION

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

get_initial_state

View source

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

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.