Hardsigmoid

class torch.nn.Hardsigmoid(inplace=False)

Applies the Hardsigmoid function element-wise.

Hardsigmoid is defined as:

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

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.

Examples:

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