Mish#
- class brainstate.nn.Mish(name=None)#
Applies the Mish function, element-wise.
Mish: A Self Regularized Non-Monotonic Neural Activation Function.
\[\text{Mish}(x) = x * \text{Tanh}(\text{Softplus}(x))\]Notes
See Mish: A Self Regularized Non-Monotonic Neural Activation Function
Shape#
Input: \((*)\), where \(*\) means any number of dimensions.
Output: \((*)\), same shape as the input.
Examples
>>> import brainstate.nn as nn >>> import brainstate >>> m = nn.Mish() >>> x = brainstate.random.randn(2) >>> output = m(x)