![]() |
Class UGRNNCell
Update Gate Recurrent Neural Network (UGRNN) cell.
Inherits From: RNNCell
Compromise between a LSTM/GRU and a vanilla RNN. There is only one gate, and that is to determine whether the unit should be integrating or computing instantaneously. This is the recurrent idea of the feedforward Highway Network.
This implements the recurrent cell from the paper:
https://arxiv.org/abs/1611.09913
Jasmine Collins, Jascha Sohl-Dickstein, and David Sussillo. "Capacity and Trainability in Recurrent Neural Networks" Proc. ICLR 2017.
__init__
__init__(
num_units,
initializer=None,
forget_bias=1.0,
activation=tf.math.tanh,
reuse=None
)
Initialize the parameters for an UGRNN cell.
Args:
num_units
: int, The number of units in the UGRNN cellinitializer
: (optional) The initializer to use for the weight matrices.forget_bias
: (optional) float, default 1.0, The initial bias of the forget gate, used to reduce the scale of forgetting at the beginning of the training.activation
: (optional) Activation function of the inner states. Default istf.tanh
.reuse
: (optional) Python boolean describing whether to reuse variables in an existing scope. If notTrue
, and the existing scope already has the given variables, an error is raised.
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
tf.contrib.rnn.UGRNNCell.get_initial_state
get_initial_state(
inputs=None,
batch_size=None,
dtype=None
)
tf.contrib.rnn.UGRNNCell.zero_state
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
.