:nosearch:

.. _op_ai_onnx_InstanceNormalization-1:

InstanceNormalization - version 1
=================================

This page documents version **1** of operator **InstanceNormalization**. See :doc:`InstanceNormalization` for the latest version (since version 22).

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

Carries out instance normalization as described in the paper
https://arxiv.org/abs/1607.08022.

y = scale \* (x - mean) / sqrt(variance + epsilon) + B,
where mean and variance are computed per instance per channel.

**Inputs**

- **input** (*T*): The input 4-dimensional tensor of shape NCHW.
- **scale** (*T*): The input 1-dimensional scale tensor of size C.
- **B** (*T*): The input 1-dimensional bias tensor of size C.

**Outputs**

- **output** (*T*): The output 4-dimensional tensor of the same shape as input.

**Attributes**

- **consumed_inputs** (*int[]*): legacy optimization attribute.
- **epsilon** (*float*): The epsilon value to use to avoid division by zero.

**Type Constraints**

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