Hardsigmoid — PyTorch 2.7 documentation (original) (raw)

class torch.nn.Hardsigmoid(inplace=False)[source][source]¶

Applies the Hardsigmoid function element-wise.

Hardsigmoid is defined as:

Hardsigmoid(x)={0if x≤−3,1if x≥+3,x/6+1/2otherwise\text{Hardsigmoid}(x) = \begin{cases} 0 & \text{if~} x \le -3, \\ 1 & \text{if~} x \ge +3, \\ x / 6 + 1 / 2 & \text{otherwise} \end{cases}

Parameters

inplace (bool) – can optionally do the operation in-place. Default: False

Shape:

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

../_images/Hardsigmoid.png

Examples:

m = nn.Hardsigmoid() input = torch.randn(2) output = m(input)