.. _op_ai_onnx_ArgMax-11:

ArgMax - version 11
===================

This page documents version **11** of operator **ArgMax**. See :doc:`ArgMax` for the latest version (since version 13).

- **Domain**: ``ai.onnx``
- **Since version**: 11

Computes the indices of the max elements of the input tensor's element along the provided axis.
The resulting tensor has the same rank as the input if keepdims equals 1.
If keepdims equal 0, then the resulting tensor has the reduced dimension pruned.
The input tensor must not be empty.
The type of the output tensor is integer.

**Inputs**

- **data** (*T*): An input tensor.

**Outputs**

- **reduced** (*tensor(int64)*): Reduced output tensor with integer data type.

**Type Constraints**

- **T**: Constrain input and output types to all numeric tensors.
  Allowed types: tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8).

Differences with previous version (1)
-------------------------------------

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

* old version: 1
* new version: 11
* breaking: no

**Documentation:**

* line similarity: 0.89 (+1/-0 lines)

.. code-block:: diff

    --- ArgMax v1
    +++ ArgMax v11
    @@ -1,4 +1,5 @@
     Computes the indices of the max elements of the input tensor's element along the provided axis.
     The resulting tensor has the same rank as the input if keepdims equals 1.
     If keepdims equal 0, then the resulting tensor has the reduced dimension pruned.
    +The input tensor must not be empty.
     The type of the output tensor is integer.