Mish - version 18#

This page documents version 18 of operator Mish. See Mish for the latest version (since version 22).

  • Domain: ai.onnx

  • Since version: 18

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

Perform the linear unit element-wise on the input tensor X using formula:

mish(x) = x * tanh(softplus(x)) = x * tanh(ln(1 + e^{x}))

Inputs

  • X (T): Input tensor

Outputs

  • Y (T): Output tensor

Type Constraints

  • T: Constrain input X and output types to float tensors. Allowed types: tensor(double), tensor(float), tensor(float16).