.. _op_ai_onnx_ml_Binarizer:

Binarizer
=========

- **Domain**: ``ai.onnx.ml``
- **Since version**: 1

Maps the values of the input tensor to either 0 or 1, element-wise, based on the outcome of a comparison against a threshold value.

**Inputs**

- **X** (*T*): Data to be binarized

**Outputs**

- **Y** (*T*): Binarized output data

**Type Constraints**

- **T**: The input must be a tensor of a numeric type. The output will be of the same tensor type.
  Allowed types: tensor(double), tensor(float), tensor(int32), tensor(int64).

Examples
--------

**test_cc_binarizer_float**

.. code-block:: text

    Attributes:
      threshold = 1.0

.. code-block:: text

    Inputs:
      x: shape=(2, 4), dtype=float32
        [[ 0.5,  1. ,  1.5,  2. ],
         [-1. ,  1. ,  3. ,  0.9]]

    Outputs:
      y: shape=(2, 4), dtype=float32
        [[0., 0., 1., 1.],
         [0., 0., 1., 0.]]

**test_cc_binarizer_int64**

.. code-block:: text

    Attributes:
      threshold = 3.0

.. code-block:: text

    Inputs:
      x: shape=(5,), dtype=int64
        [ 0,  3,  4, -2, 10]

    Outputs:
      y: shape=(5,), dtype=int64
        [0, 0, 1, 0, 1]