Mish#

classtorch.nn.modules.activation.Mish(inplace=False)[source]#

Applies the Mish function, element-wise.

Mish: A Self Regularized Non-Monotonic Neural Activation Function.

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

Note

SeeMish: A Self Regularized Non-Monotonic Neural Activation Function

Shape:

• Input:$(\ast )$(∗), where$\ast$∗ means any number of dimensions.

• Output:$(\ast )$(∗), same shape as the input.

Examples:

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

extra_repr()[source]#

Return the extra representation of the module.

Return type

str

forward(input)[source]#

Runs the forward pass.

Return type

Tensor