LogSigmoid

class torch.nn.LogSigmoid(*args, **kwargs) [source]

Applies the element-wise function:

$$\text{LogSigmoid}(x) = \log\left(\frac{ 1 }{ 1 + \exp(-x)}\right)$$

Shape:

• Input: $(*)$, where $*$ means any number of dimensions.
• Output: $(*)$, same shape as the input.

Examples:

>>> m = nn.LogSigmoid()
>>> input = torch.randn(2)
>>> output = m(input)