.. _l-onnx-doc-ImageScaler:

===========
ImageScaler
===========

.. contents::
    :local:


.. _l-onnx-op-imagescaler-1:

ImageScaler - 1
===============

**Version**

* **name**: `ImageScaler (GitHub) <https://github.com/onnx/onnx/blob/main/docs/Operators.md#ImageScaler>`_
* **domain**: **main**
* **since_version**: **1**
* **function**:
* **support_level**:
* **shape inference**:

This version of the operator has been available
**since version 1**.

**Summary**

Scale and bias the input image. Bias values are stored in
the same ordering as the image pixel format.

**Attributes**

* **bias**:
  Bias applied to each channel, same size as C. Default value is ``?``.
* **scale**:
  The scale to apply. Default value is ``?``.

**Inputs**

* **input** (heterogeneous) - **T**:
  Input tensor of shape [N,C,H,W]

**Outputs**

* **output** (heterogeneous) - **T**:
  Result, has same shape and type as input

**Examples**