技術標籤：PytorchpytorchLogSoftmax

LOGSOFTMAX

CLASS torch.nn.LogSoftmax(dim: Optional[int] = None)

將函式應用於n維輸入張量。 LogSoftmax公式可以簡化為：

Shape:

• Input:(∗)where∗means, any number of additional dimensions

• Output:(∗), same shape as the input

Parameters

dim(int) – A dimension along whichLogSoftmaxwill be computed.用來計算LogSoftmax的維度。

Returns

a Tensor of the same dimension and shape as the input with values in the range [-inf, 0)。與輸入具有相同維度和形狀的張量，其值在[-inf，0）範圍內。

Examples:

>>> m = nn.LogSoftmax()
>>> input = torch.randn(2, 3)
>>> output = m(input)