![]() |
Class GLSTMCell
Group LSTM cell (G-LSTM).
Inherits From: RNNCell
The implementation is based on:
https://arxiv.org/abs/1703.10722
O. Kuchaiev and B. Ginsburg "Factorization Tricks for LSTM Networks", ICLR 2017 workshop.
In brief, a G-LSTM cell consists of one LSTM sub-cell per group, where each sub-cell operates on an evenly-sized sub-vector of the input and produces an evenly-sized sub-vector of the output. For example, a G-LSTM cell with 128 units and 4 groups consists of 4 LSTMs sub-cells with 32 units each. If that G-LSTM cell is fed a 200-dim input, then each sub-cell receives a 50-dim part of the input and produces a 32-dim part of the output.
__init__
__init__(
num_units,
initializer=None,
num_proj=None,
number_of_groups=1,
forget_bias=1.0,
activation=tf.math.tanh,
reuse=None
)
Initialize the parameters of G-LSTM cell.
Args:
num_units
: int, The number of units in the G-LSTM cellinitializer
: (optional) The initializer to use for the weight and projection matrices.num_proj
: (optional) int, The output dimensionality for the projection matrices. If None, no projection is performed.number_of_groups
: (optional) int, number of groups to use. Ifnumber_of_groups
is 1, then it should be equivalent to LSTM cellforget_bias
: Biases of the forget gate are initialized by default to 1 in order to reduce the scale of forgetting at the beginning of the training.activation
: Activation function of the inner states.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.
Raises:
ValueError
: Ifnum_units
ornum_proj
is not divisible bynumber_of_groups
.
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.GLSTMCell.get_initial_state
get_initial_state(
inputs=None,
batch_size=None,
dtype=None
)
tf.contrib.rnn.GLSTMCell.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
.