GRUCell
-
class torch.nn.GRUCell(input_size, hidden_size, bias=True)
[source] -
A gated recurrent unit (GRU) cell
where is the sigmoid function, and is the Hadamard product.
- Parameters
-
-
input_size – The number of expected features in the input
x
-
hidden_size – The number of features in the hidden state
h
-
bias – If
False
, then the layer does not use bias weightsb_ih
andb_hh
. Default:True
-
input_size – The number of expected features in the input
- Inputs: input, hidden
-
-
input of shape
(batch, input_size)
: tensor containing input features -
hidden of shape
(batch, hidden_size)
: tensor containing the initial hidden state for each element in the batch. Defaults to zero if not provided.
-
input of shape
- Outputs: h’
-
-
h’ of shape
(batch, hidden_size)
: tensor containing the next hidden state for each element in the batch
-
h’ of shape
- Shape:
-
- Input1: tensor containing input features where =
input_size
- Input2: tensor containing the initial hidden state for each element in the batch where =
hidden_size
Defaults to zero if not provided. - Output: tensor containing the next hidden state for each element in the batch
- Input1: tensor containing input features where =
- Variables
-
-
~GRUCell.weight_ih – the learnable input-hidden weights, of shape
(3*hidden_size, input_size)
-
~GRUCell.weight_hh – the learnable hidden-hidden weights, of shape
(3*hidden_size, hidden_size)
-
~GRUCell.bias_ih – the learnable input-hidden bias, of shape
(3*hidden_size)
-
~GRUCell.bias_hh – the learnable hidden-hidden bias, of shape
(3*hidden_size)
-
~GRUCell.weight_ih – the learnable input-hidden weights, of shape
Note
All the weights and biases are initialized from where
Examples:
>>> rnn = nn.GRUCell(10, 20) >>> input = torch.randn(6, 3, 10) >>> hx = torch.randn(3, 20) >>> output = [] >>> for i in range(6): hx = rnn(input[i], hx) output.append(hx)
© 2019 Torch Contributors
Licensed under the 3-clause BSD License.
https://pytorch.org/docs/1.8.0/generated/torch.nn.GRUCell.html