GRUCell

class torch.nn.modules.rnn.GRUCell(input_size, hidden_size, bias=True, device=None, dtype=None)

一个门控循环单元 (GRU) 单元。

$$\begin{array}{ll} r = \sigma(W_{ir} x + b_{ir} + W_{hr} h + b_{hr}) \\ z = \sigma(W_{iz} x + b_{iz} + W_{hz} h + b_{hz}) \\ n = \tanh(W_{in} x + b_{in} + r \odot (W_{hn} h + b_{hn})) \\ h' = (1 - z) \odot n + z \odot h \end{array}$$

其中 $\sigma$ 是 sigmoid 函数，$\odot$ 是 Hadamard 积。

参数

• input_size (int) – 输入 x 中预期的特征数量

• hidden_size (int) – 隐藏状态 h 中的特征数量

• bias (bool) – 如果为 False，则该层不使用偏置权重 b_ih 和 b_hh。默认值：True

输入：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.

输出：h’

• h’ : tensor containing the next hidden state for each element in the batch

形状

• 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。若未提供，则默认为零。

• output: $(N, H_{out})$ or $(H_{out})$ tensor containing the next hidden state。

变量

• weight_ih (torch.Tensor) – the learnable input-hidden weights, of shape (3*hidden_size, input_size)

• weight_hh (torch.Tensor) – 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)

注意

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

在某些 ROCm 设备上，当使用 float16 输入时，此模块将对反向传播使用不同精度。

示例

>>> 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)