openvino/docs/ops/activation/SoftMax_8.md

SoftMax

@sphinxdirective

Versioned name: SoftMax-8

Category: Activation function

Short description: Reference <https://github.com/Kulbear/deep-learning-nano-foundation/wiki/ReLU-and-Softmax-Activation-Functions#softmax>__

Detailed description: Reference <http://cs231n.github.io/linear-classify/#softmax>__

Attributes

• axis

  • Description: axis represents the axis of which the SoftMax is calculated. Negative value means counting dimensions from the back. axis equal 1 is a default value.
  • Range of values: [-rank, rank - 1]
  • Type: int
  • Default value: 1
  • Required: no

Mathematical Formulation

.. math::

y_{c} = \frac{e^{Z_{c}}}{\sum_{d=1}^{C}e^{Z_{d}}}

where :math:C is a size of tensor along axis dimension.

Inputs:

• 1: Input tensor with enough number of dimension to be compatible with axis attribute. Required.

Outputs:

• 1: The resulting tensor of the same shape and type as input tensor.

Example

.. code-block:: cpp

<layer ... type="SoftMax" ... > ... ...

@endsphinxdirective