torch.nn.functional.mish#

torch.nn.functional.mish(input,inplace=False)[source]#

Apply 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

SeeMish for more details.

Return type

Tensor