W3cubDocs

/PyTorch 2.9

torch.nn.functional.hardswish

torch.nn.functional.hardswish(input, inplace=False) [source]

Apply hardswish function, element-wise.

Follows implementation as described in the paper: Searching for MobileNetV3.

Hardswish(x)={0if x3,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}

See Hardswish for more details.

Return type

Tensor

© 2025, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://docs.pytorch.org/docs/2.9/generated/torch.nn.functional.hardswish.html