Softsign#

classtorch.nn.Softsign(*args,**kwargs)[source]#

Applies the element-wise Softsign function.

$$\text{SoftSign}(x)=\frac{x}{1+\mathrm{\mid }x\mathrm{\mid }}$$SoftSign(x)=1+∣x∣x​

Shape:

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

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

Examples:

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

forward(input)[source]#

Runs the forward pass.

Return type:

Tensor