There are two variants. The default one is based on 1406.1078v3 and has reset gate applied to hidden state before matrix multiplication. The other one is based on original 1406.1078v1 and has the order reversed.
layer_gru( object, units, activation = "tanh", recurrent_activation = "sigmoid", use_bias = TRUE, return_sequences = FALSE, return_state = FALSE, go_backwards = FALSE, stateful = FALSE, unroll = FALSE, time_major = FALSE, reset_after = TRUE, kernel_initializer = "glorot_uniform", recurrent_initializer = "orthogonal", bias_initializer = "zeros", kernel_regularizer = NULL, recurrent_regularizer = NULL, bias_regularizer = NULL, activity_regularizer = NULL, kernel_constraint = NULL, recurrent_constraint = NULL, bias_constraint = NULL, dropout = 0, recurrent_dropout = 0, ... )
object  What to compose the new


units  Positive integer, dimensionality of the output space. 
activation  Activation function to use. Default: hyperbolic tangent
( 
recurrent_activation  Activation function to use for the recurrent step. 
use_bias  Boolean, whether the layer uses a bias vector. 
return_sequences  Boolean. Whether to return the last output in the output sequence, or the full sequence. 
return_state  Boolean (default FALSE). Whether to return the last state in addition to the output. 
go_backwards  Boolean (default FALSE). If TRUE, process the input sequence backwards and return the reversed sequence. 
stateful  Boolean (default FALSE). If TRUE, the last state for each sample at index i in a batch will be used as initial state for the sample of index i in the following batch. 
unroll  Boolean (default FALSE). If TRUE, the network will be unrolled, else a symbolic loop will be used. Unrolling can speedup a RNN, although it tends to be more memoryintensive. Unrolling is only suitable for short sequences. 
time_major  If True, the inputs and outputs will be in shape

reset_after  GRU convention (whether to apply reset gate after or before matrix multiplication). FALSE = "before" (default), TRUE = "after" (CuDNN compatible). 
kernel_initializer  Initializer for the 
recurrent_initializer  Initializer for the 
bias_initializer  Initializer for the bias vector. 
kernel_regularizer  Regularizer function applied to the 
recurrent_regularizer  Regularizer function applied to the

bias_regularizer  Regularizer function applied to the bias vector. 
activity_regularizer  Regularizer function applied to the output of the layer (its "activation").. 
kernel_constraint  Constraint function applied to the 
recurrent_constraint  Constraint function applied to the

bias_constraint  Constraint function applied to the bias vector. 
dropout  Float between 0 and 1. Fraction of the units to drop for the linear transformation of the inputs. 
recurrent_dropout  Float between 0 and 1. Fraction of the units to drop for the linear transformation of the recurrent state. 
...  Standard Layer args. 
The second variant is compatible with CuDNNGRU (GPUonly) and allows
inference on CPU. Thus it has separate biases for kernel
and
recurrent_kernel
. Use reset_after = TRUE
and
recurrent_activation = "sigmoid"
.
ND tensor with shape (batch_size, timesteps, ...)
,
or (timesteps, batch_size, ...)
when time_major = TRUE
.
if return_state
: a list of tensors. The first tensor is
the output. The remaining tensors are the last states,
each with shape (batch_size, state_size)
, where state_size
could be a high dimension tensor shape.
if return_sequences
: ND tensor with shape [batch_size, timesteps, output_size]
, where output_size
could be a high dimension tensor shape, or
[timesteps, batch_size, output_size]
when time_major
is TRUE
else, ND tensor with shape [batch_size, output_size]
, where
output_size
could be a high dimension tensor shape.
This layer supports masking for input data with a variable number of
timesteps. To introduce masks to your data, use
layer_embedding()
with the mask_zero
parameter set to TRUE
.
You can set RNN layers to be 'stateful', which means that the states computed for the samples in one batch will be reused as initial states for the samples in the next batch. This assumes a onetoone mapping between samples in different successive batches.
For intuition behind statefulness, there is a helpful blog post here: https://philipperemy.github.io/kerasstatefullstm/
To enable statefulness:
Specify stateful = TRUE
in the layer constructor.
Specify a fixed batch size for your model. For sequential models,
pass batch_input_shape = list(...)
to the first layer in your model.
For functional models with 1 or more Input layers, pass
batch_shape = list(...)
to all the first layers in your model.
This is the expected shape of your inputs including the batch size.
It should be a list of integers, e.g. list(32, 10, 100)
.
For dimensions which can vary (are not known ahead of time),
use NULL
in place of an integer, e.g. list(32, NULL, NULL)
.
Specify shuffle = FALSE
when calling fit()
.
To reset the states of your model, call layer$reset_states()
on either
a specific layer, or on your entire model.
You can specify the initial state of RNN layers symbolically by calling them
with the keyword argument initial_state.
The value of initial_state should
be a tensor or list of tensors representing the initial state of the RNN
layer.
You can specify the initial state of RNN layers numerically by calling
reset_states
with the named argument states.
The value of states
should
be an array or list of arrays representing the initial state of the RNN
layer.
You can pass "external" constants to the cell using the constants
named
argument of RNN$__call__
(as well as RNN$call
) method. This requires that the
cell$call
method accepts the same keyword argument constants
. Such constants
can be used to condition the cell transformation on additional static inputs
(not changing over time), a.k.a. an attention mechanism.
Learning Phrase Representations using RNN EncoderDecoder for Statistical Machine Translation
On the Properties of Neural Machine Translation: EncoderDecoder Approaches
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
Other recurrent layers:
layer_cudnn_gru()
,
layer_cudnn_lstm()
,
layer_lstm()
,
layer_rnn()
,
layer_simple_rnn()