.. _op_ai_onnx_Mish:

Mish
====

- **Domain**: ``ai.onnx``
- **Since version**: 22

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

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

.. code-block::

    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(bfloat16), tensor(double), tensor(float), tensor(float16).

Examples
--------

**test_cc_mish**

.. code-block:: text

    Node:
      Mish(X) -> (Y)

.. code-block:: text

    Inputs:
      X: shape=(2, 3), dtype=float32
        [[-4., -1.,  0.],
         [ 1.,  2.,  4.]]

    Outputs:
      Y: shape=(2, 3), dtype=float32
        [[-0.07259175, -0.30340144,  0.        ],
         [ 0.8650984 ,  1.943959  ,  3.997413  ]]

Differences with previous version (18)
--------------------------------------

**SchemaDiff**: ``Mish`` (domain ``'ai.onnx'``)

* old version: 18
* new version: 22
* breaking: no

**Type constraints:**

* changed 'T': added types: ['tensor(bfloat16)']

Version History
---------------

- :doc:`Version 18 <Mish-18>`