Cell class for the LSTM layer.

This class processes one step within the whole time sequence input, whereas layer_lstm() processes the whole sequence.

Usage

rnn_cell_lstm(
  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,
  kernel_constraint = NULL,
  recurrent_constraint = NULL,
  bias_constraint = NULL,
  dropout = 0,
  recurrent_dropout = 0,
  seed = NULL,
  ...
)

Arguments

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".
unit_forget_bias: Boolean (default TRUE). If TRUE, add 1 to the bias of the forget gate at initialization. Setting it to TRUE will also force bias_initializer="zeros". This is recommended in Jozefowicz et al.
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.
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.
...: For forward/backward compatability.

Value

A Layer instance, which is intended to be used with layer_rnn().

Call Arguments

inputs: A 2D tensor, with shape (batch, features).
states: A 2D tensor with shape (batch, units), which is the state from the previous time step.
training: Boolean indicating whether the layer should behave in training mode or in inference mode. Only relevant when dropout or recurrent_dropout is used.

Examples

inputs <- random_uniform(c(32, 10, 8))
output <- inputs |>
  layer_rnn(cell = rnn_cell_lstm(4))
shape(output)

## shape(32, 4)

rnn <- layer_rnn(cell = rnn_cell_lstm(4),
                 return_sequences = T,
                 return_state = T)
c(whole_sequence_output, ...final_state) %<-% rnn(inputs)
str(whole_sequence_output)

## <tf.Tensor: shape=(32, 10, 4), dtype=float32, numpy=…>

str(final_state)

## List of 2
##  $ :<tf.Tensor: shape=(32, 4), dtype=float32, numpy=…>
##  $ :<tf.Tensor: shape=(32, 4), dtype=float32, numpy=…>

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_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_simple()
rnn_cells_stack()

Usage

Arguments

Value

Call Arguments

Examples

See also