Hardswish¶

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

Applies the hardswish function, element-wise, as described in the paper:

Searching for MobileNetV3.

$$\text{Hardswish}(x) = \begin{cases} 0 & \text{if~} x \le -3, \\ x & \text{if~} x \ge +3, \\ x \cdot (x + 3) /6 & \text{otherwise} \end{cases}$$

Parameters

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

Shape:

• Input: $(N, *)$ where * means, any number of additional dimensions

• Output: $(N, *)$ , same shape as the input

Examples:

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