Mish

API

class warp_nn.modules.activations.Mish(*, requires_grad: bool = True)

Bases: Module

Mish activation function.

This class computes the element-wise Mish activation function:

\[\text{Mish}(x) = x \tanh(\text{softplus}(x)) = x \tanh\left(\ln\left(1 + e^x\right)\right)\]

Parameters:

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

__call__(input: array) → array

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.