(l-onnx-doc-PRelu)=

# PRelu


(l-onnx-op-prelu-16)=

## PRelu - 16

### Version

- **name**: [PRelu (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#PRelu)
- **domain**: `main`
- **since_version**: `16`
- **function**: `True`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 16**.

### Summary

PRelu takes input data (Tensor<T>) and slope tensor as input, and produces one
output data (Tensor<T>) where the function `f(x) = slope * x for x < 0`,
`f(x) = x for x >= 0`., is applied to the data tensor elementwise.
This operator supports **unidirectional broadcasting** (tensor slope should be unidirectional broadcastable to input tensor X); for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).

#### Function Body

The function definition for this operator.

```
<
  domain: "",
  opset_import: ["" : 16]
>
PRelu (X, slope) => (Y)
{
   Zero = Constant <value: tensor = float {0}> ()
   ZeroCast = CastLike (Zero, X)
   XLessThanZero = Less (X, ZeroCast)
   SlopeMulX = Mul (slope, X)
   Y = Where (XLessThanZero, SlopeMulX, X)
}
```

### Inputs

- **X** (heterogeneous) - **T**:

  Input tensor
- **slope** (heterogeneous) - **T**:

  Slope tensor. The shape of slope can be smaller than first input X; if so, its shape must be unidirectional broadcastable to X

### Outputs

- **Y** (heterogeneous) - **T**:

  Output tensor (same size as X)

### Type Constraints

* **T** in ( `tensor(bfloat16)`, `tensor(double)`, `tensor(float)`, `tensor(float16)`, `tensor(int32)`, `tensor(int64)`, `tensor(uint32)`, `tensor(uint64)` ):

  Constrain input and output types to float/int tensors.

```{toctree}
text_diff_PRelu_9_16
```

(l-onnx-op-prelu-9)=

## PRelu - 9

### Version

- **name**: [PRelu (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#PRelu)
- **domain**: `main`
- **since_version**: `9`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 9**.

### Summary

PRelu takes input data (Tensor<T>) and slope tensor as input, and produces one
output data (Tensor<T>) where the function `f(x) = slope * x for x < 0`,
`f(x) = x for x >= 0`., is applied to the data tensor elementwise.
This operator supports **unidirectional broadcasting** (tensor slope should be unidirectional broadcastable to input tensor X); for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).

### Inputs

- **X** (heterogeneous) - **T**:

  Input tensor
- **slope** (heterogeneous) - **T**:

  Slope tensor. The shape of slope can be smaller than first input X; if so, its shape must be unidirectional broadcastable to X

### Outputs

- **Y** (heterogeneous) - **T**:

  Output tensor (same size as X)

### Type Constraints

* **T** in ( `tensor(double)`, `tensor(float)`, `tensor(float16)`, `tensor(int32)`, `tensor(int64)`, `tensor(uint32)`, `tensor(uint64)` ):

  Constrain input and output types to float/int tensors.

```{toctree}
text_diff_PRelu_7_16
text_diff_PRelu_7_9
```

(l-onnx-op-prelu-7)=

## PRelu - 7

### Version

- **name**: [PRelu (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#PRelu)
- **domain**: `main`
- **since_version**: `7`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 7**.

### Summary

PRelu takes input data (Tensor<T>) and slope tensor as input, and produces one
output data (Tensor<T>) where the function `f(x) = slope * x for x < 0`,
`f(x) = x for x >= 0`., is applied to the data tensor elementwise.
This operator supports **unidirectional broadcasting** (tensor slope should be unidirectional broadcastable to input tensor X); for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).

### Inputs

- **X** (heterogeneous) - **T**:

  Input tensor
- **slope** (heterogeneous) - **T**:

  Slope tensor. The shape of slope can be smaller than first input X; if so, its shape must be unidirectional broadcastable to X

### Outputs

- **Y** (heterogeneous) - **T**:

  Output tensor (same size as X)

### Type Constraints

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

  Constrain input and output types to float tensors.

```{toctree}
text_diff_PRelu_6_16
text_diff_PRelu_6_9
text_diff_PRelu_6_7
```

(l-onnx-op-prelu-6)=

## PRelu - 6

### Version

- **name**: [PRelu (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#PRelu)
- **domain**: `main`
- **since_version**: `6`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 6**.

### Summary

PRelu takes input data (Tensor<T>) and slope tensor as input, and produces one
output data (Tensor<T>) where the function `f(x) = slope * x for x < 0`,
`f(x) = x for x >= 0`., is applied to the data tensor elementwise.

### Inputs

- **X** (heterogeneous) - **T**:

  Input tensor
- **slope** (heterogeneous) - **T**:

  Slope tensor. If `Slope` is of size 1, the value is sharedacross different channels

### Outputs

- **Y** (heterogeneous) - **T**:

  Output tensor

### Type Constraints

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

  Constrain input and output types to float tensors.

```{toctree}
text_diff_PRelu_1_16
text_diff_PRelu_1_9
text_diff_PRelu_1_7
text_diff_PRelu_1_6
```

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

## PRelu - 1

### Version

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

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

### Summary

PRelu takes input data (Tensor<T>) and slope tensor as input, and produces one
output data (Tensor<T>) where the function `f(x) = slope * x for x < 0`,
`f(x) = x for x >= 0`., is applied to the data tensor elementwise.

### Attributes

* **consumed_inputs - INTS** :

  legacy optimization attribute.

### Inputs

- **X** (heterogeneous) - **T**:

  Input tensor
- **slope** (heterogeneous) - **T**:

  Slope tensor. If `Slope` is of size 1, the value is sharedacross different channels

### Outputs

- **Y** (heterogeneous) - **T**:

  Output tensor

### Type Constraints

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

  Constrain input and output types to float tensors.