LSTMCell ¬

class torch.ao.nn.quantized.dynamic.LSTMCell(*args, **kwargs)[source][source] ¬

长短期记忆（LSTM）单元。

一个以浮点张量作为输入和输出的动态量化 LSTMCell 模块。权重量化为 8 位。我们采用与 torch.nn.LSTMCell 相同的接口，请参阅 https://pytorch.org/docs/stable/nn.html#torch.nn.LSTMCell 以获取文档。

示例：

>>> rnn = nn.LSTMCell(10, 20)
>>> input = torch.randn(6, 3, 10)
>>> hx = torch.randn(3, 20)
>>> cx = torch.randn(3, 20)
>>> output = []
>>> for i in range(6):
...     hx, cx = rnn(input[i], (hx, cx))
...     output.append(hx)