Hard Swish (HardSwish)#

API#

class warp_nn.modules.activations.HardSwish(*, requires_grad: bool = True)[source]#

Bases: Module

Hard Swish (HardSwish) activation function.

This class computes the element-wise Hard Swish activation function:

\[\text{HardSwish}(x) = x \, \frac{\min(\max(x + 3, 0), 6)}{6}\]
Parameters:

requires_grad – Whether the cached output arrays of the module require gradients.

__call__(
input: array,
) → array[source]#

Forward pass of the activation function.

Parameters:

input – The input array, with up to 3 dimensions.

Returns:

The output array, with same shape as the input array.

Raises:

TypeError – If the input array’s data type or number of dimensions is not supported.