Hardswish — PyTorch 2.7 documentation (original) (raw)

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

Applies the Hardswish function, element-wise.

Method described in the paper: Searching for MobileNetV3.

Hardswish is defined as:

Hardswish(x)={0if x≤−3,xif x≥+3,x⋅(x+3)/6otherwise\text{Hardswish}(x) = \begin{cases} 0 & \text{if~} x \le -3, \\ x & \text{if~} x \ge +3, \\ x \cdot (x + 3) /6 & \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/Hardswish.png

Examples:

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