oneflow.nn.GRUCell¶
-
class
oneflow.nn.
GRUCell
(input_size: int, hidden_size: int, bias: bool = True, device=None, dtype=None)¶ A gated recurrent unit (GRU) cell
\[\begin{split}\begin{array}{ll} r = \sigma(W_{ir} x + b_{ir} + W_{hr} h + b_{hr}) \\ z = \sigma(W_{iz} x + b_{iz} + W_{hz} h + b_{hz}) \\ n = \tanh(W_{in} x + b_{in} + r * (W_{hn} h + b_{hn})) \\ h' = (1 - z) * n + z * h \end{array}\end{split}\]where \(\sigma\) is the sigmoid function, and \(*\) is the Hadamard product.
The interface is consistent with PyTorch. The documentation is referenced from: https://pytorch.org/docs/1.10/generated/torch.nn.GRUCell.html.
- 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 weights b_ih and b_hh. Default:True
- Inputs: input, hidden
input : tensor containing input features
hidden : tensor containing the initial hidden state for each element in the batch. Defaults to zero if not provided.
- Outputs: h’
h’ : tensor containing the next hidden state for each element in the batch
- Shape:
input: \((N, H_{in})\) or \((H_{in})\) tensor containing input features where \(H_{in}\) = input_size.
hidden: \((N, H_{out})\) or \((H_{out})\) tensor containing the initial hidden state where \(H_{out}\) = hidden_size. Defaults to zero if not provided.
output: \((N, H_{out})\) or \((H_{out})\) tensor containing the next hidden state.
-
weight_ih
¶ the learnable input-hidden weights, of shape (3*hidden_size, input_size)
-
weight_hh
¶ the learnable hidden-hidden weights, of shape (3*hidden_size, hidden_size)
-
bias_ih
¶ the learnable input-hidden bias, of shape (3*hidden_size)
-
bias_hh
¶ the learnable hidden-hidden bias, of shape (3*hidden_size)
Note
All the weights and biases are initialized from \(\mathcal{U}(-\sqrt{k}, \sqrt{k})\) where \(k = \frac{1}{\text{hidden\_size}}\)
For example:
>>> import oneflow as flow >>> import oneflow.nn as nn >>> rnn = nn.GRUCell(10, 20) >>> input = flow.randn(6, 3, 10) >>> hx = flow.randn(3, 20) >>> hx = rnn(input[0], hx) >>> hx.size() oneflow.Size([3, 20])