Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or backend-native) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the cuDNN kernel (see below for details), the layer will use a fast cuDNN implementation when using the TensorFlow backend.

The requirements to use the cuDNN implementation are:

`activation`

==`tanh`

`recurrent_activation`

==`sigmoid`

`dropout`

== 0 and`recurrent_dropout`

== 0`unroll`

is`FALSE`

`use_bias`

is`TRUE`

`reset_after`

is`TRUE`

Inputs, if use masking, are strictly right-padded.

Eager execution is enabled in the outermost context.

There are two variants of the GRU implementation. The default one is based on v3 and has reset gate applied to hidden state before matrix multiplication. The other one is based on original and has the order reversed.

The second variant is compatible with CuDNNGRU (GPU-only) and allows
inference on CPU. Thus it has separate biases for `kernel`

and
`recurrent_kernel`

. To use this variant, set `reset_after=TRUE`

and
`recurrent_activation='sigmoid'`

.

For example:

```
inputs <- random_uniform(c(32, 10, 8))
outputs <- inputs |> layer_gru(4)
shape(outputs)
```

```
# (32, 4)
gru <- layer_gru(, 4, return_sequences = TRUE, return_state = TRUE)
c(whole_sequence_output, final_state) %<-% gru(inputs)
shape(whole_sequence_output)
```

`shape(final_state)`

## Usage

```
layer_gru(
object,
units,
activation = "tanh",
recurrent_activation = "sigmoid",
use_bias = 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,
seed = NULL,
return_sequences = FALSE,
return_state = FALSE,
go_backwards = FALSE,
stateful = FALSE,
unroll = FALSE,
reset_after = TRUE,
use_cudnn = "auto",
...
)
```

## Arguments

- object
Object to compose the layer with. A tensor, array, or sequential model.

- units
Positive integer, dimensionality of the output space.

- activation
Activation function to use. Default: hyperbolic tangent (

`tanh`

). If you pass`NULL`

, no activation is applied (ie. "linear" activation:`a(x) = x`

).- recurrent_activation
Activation function to use for the recurrent step. Default: sigmoid (

`sigmoid`

). If you pass`NULL`

, no activation is applied (ie. "linear" activation:`a(x) = x`

).- use_bias
Boolean, (default

`TRUE`

), whether the layer should use a bias vector.- kernel_initializer
Initializer for the

`kernel`

weights matrix, used for the linear transformation of the inputs. Default:`"glorot_uniform"`

.- recurrent_initializer
Initializer for the

`recurrent_kernel`

weights matrix, used for the linear transformation of the recurrent state. Default:`"orthogonal"`

.- bias_initializer
Initializer for the bias vector. Default:

`"zeros"`

.- kernel_regularizer
Regularizer function applied to the

`kernel`

weights matrix. Default:`NULL`

.- recurrent_regularizer
Regularizer function applied to the

`recurrent_kernel`

weights matrix. Default:`NULL`

.- bias_regularizer
Regularizer function applied to the bias vector. Default:

`NULL`

.- activity_regularizer
Regularizer function applied to the output of the layer (its "activation"). Default:

`NULL`

.- kernel_constraint
Constraint function applied to the

`kernel`

weights matrix. Default:`NULL`

.- recurrent_constraint
Constraint function applied to the

`recurrent_kernel`

weights matrix. Default:`NULL`

.- bias_constraint
Constraint function applied to the bias vector. Default:

`NULL`

.- dropout
Float between 0 and 1. Fraction of the units to drop for the linear transformation of the inputs. Default: 0.

- recurrent_dropout
Float between 0 and 1. Fraction of the units to drop for the linear transformation of the recurrent state. Default: 0.

- seed
Random seed for dropout.

- return_sequences
Boolean. Whether to return the last output in the output sequence, or the full sequence. Default:

`FALSE`

.- return_state
Boolean. Whether to return the last state in addition to the output. Default:

`FALSE`

.- 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 speed-up a RNN, although it tends to be more memory-intensive. Unrolling is only suitable for short sequences.- reset_after
GRU convention (whether to apply reset gate after or before matrix multiplication).

`FALSE`

is`"before"`

,`TRUE`

is`"after"`

(default and cuDNN compatible).- use_cudnn
Whether to use a cuDNN-backed implementation.

`"auto"`

will attempt to use cuDNN when feasible, and will fallback to the default implementation if not.- ...
For forward/backward compatability.

## Value

The return value depends on the value provided for the first argument.
If `object`

is:

a

`keras_model_sequential()`

, then the layer is added to the sequential model (which is modified in place). To enable piping, the sequential model is also returned, invisibly.a

`keras_input()`

, then the output tensor from calling`layer(input)`

is returned.`NULL`

or missing, then a`Layer`

instance is returned.

## Call Arguments

`inputs`

: A 3D tensor, with shape`(batch, timesteps, feature)`

.`mask`

: Binary tensor of shape`(samples, timesteps)`

indicating whether a given timestep should be masked (optional). An individual`TRUE`

entry indicates that the corresponding timestep should be utilized, while a`FALSE`

entry indicates that the corresponding timestep should be ignored. Defaults to`NULL`

.`training`

: Python boolean indicating whether the layer should behave in training mode or in inference mode. This argument is passed to the cell when calling it. This is only relevant if`dropout`

or`recurrent_dropout`

is used (optional). Defaults to`NULL`

.`initial_state`

: List of initial state tensors to be passed to the first call of the cell (optional,`NULL`

causes creation of zero-filled initial state tensors). Defaults to`NULL`

.

## See also

Other gru rnn layers: `rnn_cell_gru()`

Other rnn layers: `layer_bidirectional()`

`layer_conv_lstm_1d()`

`layer_conv_lstm_2d()`

`layer_conv_lstm_3d()`

`layer_lstm()`

`layer_rnn()`

`layer_simple_rnn()`

`layer_time_distributed()`

`rnn_cell_gru()`

`rnn_cell_lstm()`

`rnn_cell_simple()`

`rnn_cells_stack()`

Other layers: `Layer()`

`layer_activation()`

`layer_activation_elu()`

`layer_activation_leaky_relu()`

`layer_activation_parametric_relu()`

`layer_activation_relu()`

`layer_activation_softmax()`

`layer_activity_regularization()`

`layer_add()`

`layer_additive_attention()`

`layer_alpha_dropout()`

`layer_attention()`

`layer_average()`

`layer_average_pooling_1d()`

`layer_average_pooling_2d()`

`layer_average_pooling_3d()`

`layer_batch_normalization()`

`layer_bidirectional()`

`layer_category_encoding()`

`layer_center_crop()`

`layer_concatenate()`

`layer_conv_1d()`

`layer_conv_1d_transpose()`

`layer_conv_2d()`

`layer_conv_2d_transpose()`

`layer_conv_3d()`

`layer_conv_3d_transpose()`

`layer_conv_lstm_1d()`

`layer_conv_lstm_2d()`

`layer_conv_lstm_3d()`

`layer_cropping_1d()`

`layer_cropping_2d()`

`layer_cropping_3d()`

`layer_dense()`

`layer_depthwise_conv_1d()`

`layer_depthwise_conv_2d()`

`layer_discretization()`

`layer_dot()`

`layer_dropout()`

`layer_einsum_dense()`

`layer_embedding()`

`layer_feature_space()`

`layer_flatten()`

`layer_flax_module_wrapper()`

`layer_gaussian_dropout()`

`layer_gaussian_noise()`

`layer_global_average_pooling_1d()`

`layer_global_average_pooling_2d()`

`layer_global_average_pooling_3d()`

`layer_global_max_pooling_1d()`

`layer_global_max_pooling_2d()`

`layer_global_max_pooling_3d()`

`layer_group_normalization()`

`layer_group_query_attention()`

`layer_hashed_crossing()`

`layer_hashing()`

`layer_identity()`

`layer_integer_lookup()`

`layer_jax_model_wrapper()`

`layer_lambda()`

`layer_layer_normalization()`

`layer_lstm()`

`layer_masking()`

`layer_max_pooling_1d()`

`layer_max_pooling_2d()`

`layer_max_pooling_3d()`

`layer_maximum()`

`layer_mel_spectrogram()`

`layer_minimum()`

`layer_multi_head_attention()`

`layer_multiply()`

`layer_normalization()`

`layer_permute()`

`layer_random_brightness()`

`layer_random_contrast()`

`layer_random_crop()`

`layer_random_flip()`

`layer_random_rotation()`

`layer_random_translation()`

`layer_random_zoom()`

`layer_repeat_vector()`

`layer_rescaling()`

`layer_reshape()`

`layer_resizing()`

`layer_rnn()`

`layer_separable_conv_1d()`

`layer_separable_conv_2d()`

`layer_simple_rnn()`

`layer_spatial_dropout_1d()`

`layer_spatial_dropout_2d()`

`layer_spatial_dropout_3d()`

`layer_spectral_normalization()`

`layer_string_lookup()`

`layer_subtract()`

`layer_text_vectorization()`

`layer_tfsm()`

`layer_time_distributed()`

`layer_torch_module_wrapper()`

`layer_unit_normalization()`

`layer_upsampling_1d()`

`layer_upsampling_2d()`

`layer_upsampling_3d()`

`layer_zero_padding_1d()`

`layer_zero_padding_2d()`

`layer_zero_padding_3d()`

`rnn_cell_gru()`

`rnn_cell_lstm()`

`rnn_cell_simple()`

`rnn_cells_stack()`