.. _op_ai_onnx_ReduceMin-12:

ReduceMin - version 12
======================

This page documents version **12** of operator **ReduceMin**. See :doc:`ReduceMin` for the latest version (since version 20).

- **Domain**: ``ai.onnx``
- **Since version**: 12

Computes the min of the input tensor's elements along the provided axes.
The resulting tensor has the same rank as the input if keepdims equals 1.
If keepdims equals 0, then the resulting tensor has the reduced dimension pruned.
The axes attribute specifies which dimensions to reduce. Negative axes are supported.
If axes is not provided, all dimensions are reduced.
Reduction over an empty set of values yields plus infinity (if supported by the datatype) or the maximum value of the data type otherwise.

**Inputs**

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

**Outputs**

- **reduced** (*T*): Reduced output tensor.

**Attributes**

- **axes** (*int[]*): A list of integers, along which to reduce. The default is to reduce over all the dimensions of the input tensor. Accepted range is [-r, r-1] where r = rank(data).
- **keepdims** (*int*): Keep the reduced dimension or not, default 1 means keep reduced dimension.

**Type Constraints**

- **T**: Constrain input and output types to high-precision and 8 bit numeric tensors.
  Allowed types: tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(int8), tensor(uint32), tensor(uint64), tensor(uint8).

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

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

* old version: 11
* new version: 12
* breaking: no

**Type constraints:**

* changed 'T': added types: ['tensor(int8)', 'tensor(uint8)']

**Documentation:**

* line similarity: 0.20 (+5/-3 lines)

.. code-block:: diff

    --- ReduceMin v11
    +++ ReduceMin v12
    @@ -1,4 +1,6 @@
    -Computes the min of the input tensor's element along the provided axes.
    +Computes the min of the input tensor's elements along the provided axes.
     The resulting tensor has the same rank as the input if keepdims equals 1.
    -If keepdims equal 0, then the resulted tensor have the reduced dimension pruned.
    -Negative axes are supported in the axes attribute.
    +If keepdims equals 0, then the resulting tensor has the reduced dimension pruned.
    +The axes attribute specifies which dimensions to reduce. Negative axes are supported.
    +If axes is not provided, all dimensions are reduced.
    +Reduction over an empty set of values yields plus infinity (if supported by the datatype) or the maximum value of the data type otherwise.