LogSigmoid#

classtorch.nn.modules.activation.LogSigmoid(*args,**kwargs)[source]#

Applies the Logsigmoid function element-wise.

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

Shape:

• Input:$(\ast )$(∗), where$\ast$∗ means any number of dimensions.

• Output:$(\ast )$(∗), same shape as the input.

Examples:

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

forward(input)[source]#

Run forward pass.

Return type

Tensor