.. _op_ai_onnx_LogSoftmax:

LogSoftmax
==========

- **Domain**: ``ai.onnx``
- **Since version**: 13

The operator computes the log of softmax values for the given input:

.. code-block:: text

    LogSoftmax(input, axis) = Log(Softmax(input, axis=axis))

The "axis" attribute indicates the dimension along which LogSoftmax
will be performed. The output tensor has the same shape as the input tensor.

**Inputs**

- **input** (*T*): The input tensor of rank >= axis.

**Outputs**

- **output** (*T*): The output values with the same shape as the input tensor.

**Attributes**

- **axis** (*int*): Describes the dimension Softmax will be performed on. Negative value means counting dimensions from the back.

**Type Constraints**

- **T**: Constrain input and output types to float tensors.
  Allowed types: tensor(bfloat16), tensor(double), tensor(float), tensor(float16).

Examples
--------

**test_cc_logsoftmax_axis_0**

.. code-block:: text

    Node:
      LogSoftmax(input) -> (output)
      Attributes:
        axis = 0

.. code-block:: text

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

    Outputs:
      output: shape=(2, 3), dtype=float32
        [[-3.0485873 , -0.31326175, -0.01814985],
         [-0.04858732, -1.3132617 , -4.01815   ]]

**test_cc_logsoftmax_axis_1**

.. code-block:: text

    Node:
      LogSoftmax(input) -> (output)
      Attributes:
        axis = 1

.. code-block:: text

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

    Outputs:
      output: shape=(2, 3), dtype=float32
        [[-2.407606  , -1.4076059 , -0.4076059 ],
         [-0.05498505, -3.054985  , -5.054985  ]]

**test_cc_logsoftmax_axis_2**

.. code-block:: text

    Node:
      LogSoftmax(input) -> (output)
      Attributes:
        axis = 2

.. code-block:: text

    Inputs:
      input: shape=(2, 2, 3), dtype=float32
        [[[ 1. ,  2. ,  3. ],
          [ 4. ,  1. , -1. ]],
        
         [[ 0.5, -0.5,  2. ],
          [-2. ,  1.5,  0. ]]]

    Outputs:
      output: shape=(2, 2, 3), dtype=float32
        [[[-2.407606  , -1.4076059 , -0.4076059 ],
          [-0.05498505, -3.054985  , -5.054985  ]],
        
         [[-1.7663679 , -2.766368  , -0.2663679 ],
          [-3.725802  , -0.22580206, -1.7258021 ]]]

**test_cc_logsoftmax_default_axis**

.. code-block:: text

    Node:
      LogSoftmax(input) -> (output)

.. code-block:: text

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

    Outputs:
      output: shape=(2, 3), dtype=float32
        [[-2.407606  , -1.4076059 , -0.4076059 ],
         [-0.05498505, -3.054985  , -5.054985  ]]

**test_cc_logsoftmax_example_1**

.. code-block:: text

    Node:
      LogSoftmax(input) -> (output)
      Attributes:
        axis = 1

.. code-block:: text

    Inputs:
      input: shape=(2, 3), dtype=float32
        [[1., 2., 3.],
         [1., 2., 3.]]

    Outputs:
      output: shape=(2, 3), dtype=float32
        [[-2.407606 , -1.4076059, -0.4076059],
         [-2.407606 , -1.4076059, -0.4076059]]

**test_cc_logsoftmax_large_number**

.. code-block:: text

    Node:
      LogSoftmax(input) -> (output)

.. code-block:: text

    Inputs:
      input: shape=(2, 3), dtype=float32
        [[1000., 1001., 1002.],
         [1002., 1001., 1000.]]

    Outputs:
      output: shape=(2, 3), dtype=float32
        [[-2.4075928 , -1.4075928 , -0.40759277],
         [-0.40759277, -1.4075928 , -2.4075928 ]]

**test_cc_logsoftmax_negative_axis**

.. code-block:: text

    Node:
      LogSoftmax(input) -> (output)
      Attributes:
        axis = -1

.. code-block:: text

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

    Outputs:
      output: shape=(2, 3), dtype=float32
        [[-2.407606  , -1.4076059 , -0.4076059 ],
         [-0.05498505, -3.054985  , -5.054985  ]]

Differences with previous version (11)
--------------------------------------

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

* old version: 11
* new version: 13
* breaking: **yes**

**Breaking reasons:**

* attribute 'axis' (changed): default value changed 1 -> -1

**Attributes:**

* [BREAKING] changed 'axis': default value changed 1 -> -1

**Type constraints:**

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

**Documentation:**

* line similarity: 0.18 (+6/-3 lines)

.. code-block:: diff

    --- LogSoftmax v11
    +++ LogSoftmax v13
    @@ -1,4 +1,7 @@
     
    -The operator computes the logsoftmax (log of softmax) values for the given input.
    -The "axis" attribute indicates the dimension along which LogSoftmax is
    -performed. The output tensor has the same shape as the input tensor.
    +The operator computes the log of softmax values for the given input:
    +
    + LogSoftmax(input, axis) = Log(Softmax(input, axis=axis))
    +
    +The "axis" attribute indicates the dimension along which LogSoftmax
    +will be performed. The output tensor has the same shape as the input tensor.

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

- :doc:`Version 11 <LogSoftmax-11>`
- :doc:`Version 1 <LogSoftmax-1>`