LSTM¶

class
torch.nn.
LSTM
(*args, **kwargs)[source]¶ Applies a multilayer long shortterm memory (LSTM) RNN to an input sequence.
For each element in the input sequence, each layer computes the following function:
$\begin{array}{ll} \\ i_t = \sigma(W_{ii} x_t + b_{ii} + W_{hi} h_{t1} + b_{hi}) \\ f_t = \sigma(W_{if} x_t + b_{if} + W_{hf} h_{t1} + b_{hf}) \\ g_t = \tanh(W_{ig} x_t + b_{ig} + W_{hg} h_{t1} + b_{hg}) \\ o_t = \sigma(W_{io} x_t + b_{io} + W_{ho} h_{t1} + b_{ho}) \\ c_t = f_t \odot c_{t1} + i_t \odot g_t \\ h_t = o_t \odot \tanh(c_t) \\ \end{array}$where $h_t$ is the hidden state at time t, $c_t$ is the cell state at time t, $x_t$ is the input at time t, $h_{t1}$ is the hidden state of the layer at time t1 or the initial hidden state at time 0, and $i_t$ , $f_t$ , $g_t$ , $o_t$ are the input, forget, cell, and output gates, respectively. $\sigma$ is the sigmoid function, and $\odot$ is the Hadamard product.
In a multilayer LSTM, the input $x^{(l)}_t$ of the $l$ th layer ($l >= 2$ ) is the hidden state $h^{(l1)}_t$ of the previous layer multiplied by dropout $\delta^{(l1)}_t$ where each $\delta^{(l1)}_t$ is a Bernoulli random variable which is $0$ with probability
dropout
.If
proj_size > 0
is specified, LSTM with projections will be used. This changes the LSTM cell in the following way. First, the dimension of $h_t$ will be changed fromhidden_size
toproj_size
(dimensions of $W_{hi}$ will be changed accordingly). Second, the output hidden state of each layer will be multiplied by a learnable projection matrix: $h_t = W_{hr}h_t$ . Note that as a consequence of this, the output of LSTM network will be of different shape as well. See Inputs/Outputs sections below for exact dimensions of all variables. You can find more details in https://arxiv.org/abs/1402.1128. Parameters
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 LSTMs together to form a stacked LSTM, with the second LSTM taking in outputs of the first LSTM and computing the final results. Default: 1bias – 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 nonzero, introduces a Dropout layer on the outputs of each LSTM layer except the last layer, with dropout probability equal to
dropout
. Default: 0bidirectional – If
True
, becomes a bidirectional LSTM. Default:False
proj_size – If
> 0
, will use LSTM with projections of corresponding size. Default: 0
 Inputs: input, (h_0, c_0)
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. See
torch.nn.utils.rnn.pack_padded_sequence()
ortorch.nn.utils.rnn.pack_sequence()
for details.h_0 of shape (num_layers * num_directions, batch, hidden_size): tensor containing the initial hidden state for each element in the batch. If the LSTM is bidirectional, num_directions should be 2, else it should be 1. If
proj_size > 0
was specified, the shape has to be (num_layers * num_directions, batch, proj_size).c_0 of shape (num_layers * num_directions, batch, hidden_size): tensor containing the initial cell state for each element in the batch.
If (h_0, c_0) is not provided, both h_0 and c_0 default to zero.
 Outputs: output, (h_n, c_n)
output of shape (seq_len, batch, num_directions * hidden_size): tensor containing the output features (h_t) from the last layer of the LSTM, for each t. If a
torch.nn.utils.rnn.PackedSequence
has been given as the input, the output will also be a packed sequence. Ifproj_size > 0
was specified, output shape will be (seq_len, batch, num_directions * proj_size).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. If
proj_size > 0
was specified,h_n
shape will be (num_layers * num_directions, batch, proj_size).Like output, the layers can be separated using
h_n.view(num_layers, num_directions, batch, hidden_size)
and similarly for c_n.c_n of shape (num_layers * num_directions, batch, hidden_size): tensor containing the cell state for t = seq_len.
 Variables
~LSTM.weight_ih_l[k] – the learnable inputhidden weights of the $\text{k}^{th}$ layer (W_iiW_ifW_igW_io), of shape (4*hidden_size, input_size) for k = 0. Otherwise, the shape is (4*hidden_size, num_directions * hidden_size)
~LSTM.weight_hh_l[k] – the learnable hiddenhidden weights of the $\text{k}^{th}$ layer (W_hiW_hfW_hgW_ho), of shape (4*hidden_size, hidden_size). If
proj_size > 0
was specified, the shape will be (4*hidden_size, proj_size).~LSTM.bias_ih_l[k] – the learnable inputhidden bias of the $\text{k}^{th}$ layer (b_iib_ifb_igb_io), of shape (4*hidden_size)
~LSTM.bias_hh_l[k] – the learnable hiddenhidden bias of the $\text{k}^{th}$ layer (b_hib_hfb_hgb_ho), of shape (4*hidden_size)
~LSTM.weight_hr_l[k] – the learnable projection weights of the $\text{k}^{th}$ layer of shape (proj_size, hidden_size). Only present when
proj_size > 0
was specified.
Note
All the weights and biases are initialized from $\mathcal{U}(\sqrt{k}, \sqrt{k})$ where $k = \frac{1}{\text{hidden\_size}}$
Warning
There are known nondeterminism issues for RNN functions on some versions of cuDNN and CUDA. You can enforce deterministic behavior by setting the following environment variables:
On CUDA 10.1, set environment variable
CUDA_LAUNCH_BLOCKING=1
. This may affect performance.On CUDA 10.2 or later, set environment variable (note the leading colon symbol)
CUBLAS_WORKSPACE_CONFIG=:16:8
orCUBLAS_WORKSPACE_CONFIG=:4096:2
.See the cuDNN 8 Release Notes for more information.
 Orphan
Note
If the following conditions are satisfied: 1) cudnn is enabled, 2) input data is on the GPU 3) input data has dtype
torch.float16
4) V100 GPU is used, 5) input data is not inPackedSequence
format persistent algorithm can be selected to improve performance.Examples:
>>> rnn = nn.LSTM(10, 20, 2) >>> input = torch.randn(5, 3, 10) >>> h0 = torch.randn(2, 3, 20) >>> c0 = torch.randn(2, 3, 20) >>> output, (hn, cn) = rnn(input, (h0, c0))