RNNCell¶

class torch.ao.nn.quantized.dynamic.RNNCell(input_size, hidden_size, bias=True, nonlinearity='tanh', dtype=torch.qint8)[源代码]¶

具有tanh或ReLU非线性特性的Elman RNN单元。一个动态量化的RNNCell模块，输入和输出为浮点张量。权重被量化为8位。我们采用了与torch.nn.RNNCell相同的接口，请参阅https://pytorch.org/docs/stable/nn.html#torch.nn.RNNCell获取文档。

示例：

>>> rnn = nn.RNNCell(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)