LogSigmoid

class torch.nn.LogSigmoid [source]

Applies the element-wise function:

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

Shape:

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

Examples:

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