tf.contrib.rnn.NASCell

View source on GitHub

Class NASCell

Neural Architecture Search (NAS) recurrent network cell.

Inherits From: LayerRNNCell

This implements the recurrent cell from the paper:

https://arxiv.org/abs/1611.01578

Barret Zoph and Quoc V. Le. "Neural Architecture Search with Reinforcement Learning" Proc. ICLR 2017.

The class uses an optional projection layer.

__init__

View source

__init__(
    num_units,
    num_proj=None,
    use_bias=False,
    reuse=None,
    **kwargs
)

Initialize the parameters for a NAS cell.

Args:

  • num_units: int, The number of units in the NAS cell.
  • num_proj: (optional) int, The output dimensionality for the projection matrices. If None, no projection is performed.
  • use_bias: (optional) bool, If True then use biases within the cell. This is False by default.
  • reuse: (optional) Python boolean describing whether to reuse variables in an existing scope. If not True, and the existing scope already has the given variables, an error is raised.
  • **kwargs: Additional keyword arguments.

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.