nn_rnn: RNN module

nn_rnnR Documentation

RNN module

Description

Applies a multi-layer Elman RNN with \tanh or \mbox{ReLU} non-linearity to an input sequence.

Usage

nn_rnn(
  input_size,
  hidden_size,
  num_layers = 1,
  nonlinearity = NULL,
  bias = TRUE,
  batch_first = FALSE,
  dropout = 0,
  bidirectional = FALSE,
  ...
)

Arguments

input_size

The number of expected features in the input x

hidden_size

The number of features in the hidden state h

num_layers

Number of recurrent layers. E.g., setting num_layers=2 would mean stacking two RNNs together to form a ⁠stacked RNN⁠, with the second RNN taking in outputs of the first RNN and computing the final results. Default: 1

nonlinearity

The non-linearity to use. Can be either 'tanh' or 'relu'. Default: 'tanh'

bias

If FALSE, then the layer does not use bias weights b_ih and b_hh. Default: TRUE

batch_first

If TRUE, then the input and output tensors are provided as ⁠(batch, seq, feature)⁠. Default: FALSE

dropout

If non-zero, introduces a Dropout layer on the outputs of each RNN layer except the last layer, with dropout probability equal to dropout. Default: 0

bidirectional

If TRUE, becomes a bidirectional RNN. Default: FALSE

...

other arguments that can be passed to the super class.

Details

For each element in the input sequence, each layer computes the following function:

h_t = \tanh(W_{ih} x_t + b_{ih} + W_{hh} h_{(t-1)} + b_{hh})

where h_t is the hidden state at time t, x_t is the input at time t, and h_{(t-1)} is the hidden state of the previous layer at time t-1 or the initial hidden state at time 0. If nonlinearity is 'relu', then \mbox{ReLU} is used instead of \tanh.

Inputs

  • input of shape ⁠(seq_len, batch, input_size)⁠: tensor containing the features of the input sequence. The input can also be a packed variable length sequence.

  • h_0 of shape ⁠(num_layers * num_directions, batch, hidden_size)⁠: tensor containing the initial hidden state for each element in the batch. Defaults to zero if not provided. If the RNN is bidirectional, num_directions should be 2, else it should be 1.

Outputs

  • output of shape ⁠(seq_len, batch, num_directions * hidden_size)⁠: tensor containing the output features (h_t) from the last layer of the RNN, for each t. If a :class:nn_packed_sequence has been given as the input, the output will also be a packed sequence. For the unpacked case, the directions can be separated using output$view(seq_len, batch, num_directions, hidden_size), with forward and backward being direction 0 and 1 respectively. Similarly, the directions can be separated in the packed case.

  • h_n of shape ⁠(num_layers * num_directions, batch, hidden_size)⁠: tensor containing the hidden state for t = seq_len. Like output, the layers can be separated using h_n$view(num_layers, num_directions, batch, hidden_size).

Shape

  • Input1: (L, N, H_{in}) tensor containing input features where H_{in}=\mbox{input\_size} and L represents a sequence length.

  • Input2: (S, N, H_{out}) tensor containing the initial hidden state for each element in the batch. H_{out}=\mbox{hidden\_size} Defaults to zero if not provided. where S=\mbox{num\_layers} * \mbox{num\_directions} If the RNN is bidirectional, num_directions should be 2, else it should be 1.

  • Output1: (L, N, H_{all}) where H_{all}=\mbox{num\_directions} * \mbox{hidden\_size}

  • Output2: (S, N, H_{out}) tensor containing the next hidden state for each element in the batch

Attributes

  • weight_ih_l[k]: the learnable input-hidden weights of the k-th layer, of shape ⁠(hidden_size, input_size)⁠ for k = 0. Otherwise, the shape is ⁠(hidden_size, num_directions * hidden_size)⁠

  • weight_hh_l[k]: the learnable hidden-hidden weights of the k-th layer, of shape ⁠(hidden_size, hidden_size)⁠

  • bias_ih_l[k]: the learnable input-hidden bias of the k-th layer, of shape (hidden_size)

  • bias_hh_l[k]: the learnable hidden-hidden bias of the k-th layer, of shape (hidden_size)

Note

All the weights and biases are initialized from \mathcal{U}(-\sqrt{k}, \sqrt{k}) where k = \frac{1}{\mbox{hidden\_size}}

Examples

if (torch_is_installed()) {
rnn <- nn_rnn(10, 20, 2)
input <- torch_randn(5, 3, 10)
h0 <- torch_randn(2, 3, 20)
rnn(input, h0)
}

torch documentation built on May 29, 2024, 9:54 a.m.