(l-onnx-doc-LpNormalization)=

# LpNormalization


(l-onnx-op-lpnormalization-22)=

## LpNormalization - 22

### Version

- **name**: [LpNormalization (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#LpNormalization)
- **domain**: `main`
- **since_version**: `22`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 22**.

### Summary

Given a matrix, apply Lp-normalization along the provided axis.

### Attributes

* **axis - INT** (default is `'-1'`):

  The axis on which to apply normalization, -1 mean last axis.

* **p - INT** (default is `'2'`):

  The order of the normalization, only 1 or 2 are supported.

### Inputs

- **input** (heterogeneous) - **T**:

  Input matrix

### Outputs

- **output** (heterogeneous) - **T**:

  Matrix after normalization

### Type Constraints

* **T** in ( `tensor(bfloat16)`, `tensor(double)`, `tensor(float)`, `tensor(float16)` ):

  Constrain input and output types to float tensors.

```{toctree}
text_diff_LpNormalization_1_22
```

(l-onnx-op-lpnormalization-1)=

## LpNormalization - 1

### Version

- **name**: [LpNormalization (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#LpNormalization)
- **domain**: `main`
- **since_version**: `1`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

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

### Summary

Given a matrix, apply Lp-normalization along the provided axis.

### Attributes

* **axis - INT** (default is `'-1'`):

  The axis on which to apply normalization, -1 mean last axis.

* **p - INT** (default is `'2'`):

  The order of the normalization, only 1 or 2 are supported.

### Inputs

- **input** (heterogeneous) - **T**:

  Input matrix

### Outputs

- **output** (heterogeneous) - **T**:

  Matrix after normalization

### Type Constraints

* **T** in ( `tensor(double)`, `tensor(float)`, `tensor(float16)` ):

  Constrain input and output types to float tensors.