layer_lstm {keras3} | R Documentation |
Long Short-Term Memory layer - Hochreiter 1997.
Description
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 andrecurrent_dropout
== 0 -
unroll
isFALSE
-
use_bias
isTRUE
Inputs, if use masking, are strictly right-padded.
Eager execution is enabled in the outermost context.
For example:
input <- random_uniform(c(32, 10, 8)) output <- input |> layer_lstm(4) shape(output)
## shape(32, 4)
lstm <- layer_lstm(units = 4, return_sequences = TRUE, return_state = TRUE) c(whole_seq_output, final_memory_state, final_carry_state) %<-% lstm(input) shape(whole_seq_output)
## shape(32, 10, 4)
shape(final_memory_state)
## shape(32, 4)
shape(final_carry_state)
## shape(32, 4)
Usage
layer_lstm(
object,
units,
activation = "tanh",
recurrent_activation = "sigmoid",
use_bias = TRUE,
kernel_initializer = "glorot_uniform",
recurrent_initializer = "orthogonal",
bias_initializer = "zeros",
unit_forget_bias = TRUE,
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,
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 ( |
recurrent_activation |
Activation function to use
for the recurrent step.
Default: sigmoid ( |
use_bias |
Boolean, (default |
kernel_initializer |
Initializer for the |
recurrent_initializer |
Initializer for the |
bias_initializer |
Initializer for the bias vector. Default: |
unit_forget_bias |
Boolean (default |
kernel_regularizer |
Regularizer function applied to the |
recurrent_regularizer |
Regularizer function applied to the
|
bias_regularizer |
Regularizer function applied to the bias vector.
Default: |
activity_regularizer |
Regularizer function applied to the output of the
layer (its "activation"). Default: |
kernel_constraint |
Constraint function applied to the |
recurrent_constraint |
Constraint function applied to the
|
bias_constraint |
Constraint function applied to the bias vector.
Default: |
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: |
return_state |
Boolean. Whether to return the last state in addition
to the output. Default: |
go_backwards |
Boolean (default: |
stateful |
Boolean (default: |
unroll |
Boolean (default |
use_cudnn |
Whether to use a cuDNN-backed implementation. |
... |
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 callinglayer(input)
is returned.-
NULL
or missing, then aLayer
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 individualTRUE
entry indicates that the corresponding timestep should be utilized, while aFALSE
entry indicates that the corresponding timestep should be ignored. Defaults toNULL
. -
training
: 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 ifdropout
orrecurrent_dropout
is used (optional). Defaults toNULL
. -
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 toNULL
.
See Also
Other lstm rnn layers:
rnn_cell_lstm()
Other rnn layers:
layer_bidirectional()
layer_conv_lstm_1d()
layer_conv_lstm_2d()
layer_conv_lstm_3d()
layer_gru()
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_gru()
layer_hashed_crossing()
layer_hashing()
layer_identity()
layer_integer_lookup()
layer_jax_model_wrapper()
layer_lambda()
layer_layer_normalization()
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()