Mish

class torch.nn.Mish(inplace=False)

Applies the Mish function, element-wise. Mish: A Self Regularized Non-Monotonic Neural Activation Function.

$$\text{Mish}(x) = x * \text{Tanh}(\text{Softplus}(x))$$

Note

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:

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