(l-onnx-doc-Celu)=

# Celu


(l-onnx-op-celu-28)=

## Celu - 28

### Version

- **name**: [Celu (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Celu)
- **domain**: `main`
- **since_version**: `28`
- **function**: `True`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 28**.

### Summary

Continuously Differentiable Exponential Linear Units:
Perform the linear unit element-wise on the input tensor X
using formula:

```
max(0,x) + min(0,alpha*(exp(x/alpha)-1))
```

#### Function Body

The function definition for this operator.

```
<
  domain: "",
  opset_import: ["" : 28]
>
Celu <alpha>(X) => (Y)
{
   Alpha = Constant <value_float: float = @alpha> ()
   AlphaCast = CastLike (Alpha, X)
   XScaled = Div (X, AlphaCast)
   EluResult = Elu <alpha: float = 1> (XScaled)
   Y = Mul (AlphaCast, EluResult)
}
```

### Attributes

* **alpha - FLOAT** (default is `1.0`):

  The Alpha value in Celu formula which control the shape of the unit. The default value is 1.0.

### Inputs

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

  Input tensor

### Outputs

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

  Output tensor

### Type Constraints

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

  Constrain input and output types to float tensors.

### Examples

#### default

```python
import numpy as np
import onnx

alpha = 2.0
node = onnx.helper.make_node(
    "Celu",
    inputs=["X"],
    outputs=["Y"],
    alpha=alpha,
)

input_data = np.array(
    [
        [
            [[0.8439683], [0.5665144], [0.05836735]],
            [[0.02916367], [0.12964272], [0.5060197]],
            [[0.79538304], [0.9411346], [0.9546573]],
        ],
        [
            [[0.17730942], [0.46192095], [0.26480448]],
            [[0.6746842], [0.01665257], [0.62473077]],
            [[0.9240844], [0.9722341], [0.11965699]],
        ],
        [
            [[0.41356155], [0.9129373], [0.59330076]],
            [[0.81929934], [0.7862604], [0.11799799]],
            [[0.69248444], [0.54119414], [0.07513223]],
        ],
    ],
    dtype=np.float32,
)

# Calculate expected output data
positive_input = np.maximum(0, input_data)
negative_input = np.minimum(0, alpha * np.expm1(input_data / alpha))
expected_output = positive_input + negative_input

expect(node, inputs=[input_data], outputs=[expected_output], name="test_celu")
```

#### _celu_float16

```python
import numpy as np
import onnx

alpha = 2.0
node = onnx.helper.make_node(
    "Celu",
    inputs=["X"],
    outputs=["Y"],
    alpha=alpha,
)

input_data = np.array([-3.0, -0.5, 0.0, 0.5, 3.0], dtype=np.float16)

positive_input = np.maximum(0, input_data)
negative_input = np.minimum(0, alpha * np.expm1(input_data / alpha))
expected_output = (positive_input + negative_input).astype(np.float16)

expect(
    node,
    inputs=[input_data],
    outputs=[expected_output],
    name="test_celu_float16",
)
```

#### _celu_bfloat16

```python
import numpy as np
import onnx

alpha = 2.0
node = onnx.helper.make_node(
    "Celu",
    inputs=["X"],
    outputs=["Y"],
    alpha=alpha,
)

input_data = np.array([-3.0, -0.5, 0.0, 0.5, 3.0], dtype=ml_dtypes.bfloat16)

positive_input = np.maximum(0, input_data)
negative_input = np.minimum(0, alpha * np.expm1(input_data / alpha))
expected_output = (positive_input + negative_input).astype(ml_dtypes.bfloat16)

expect(
    node,
    inputs=[input_data],
    outputs=[expected_output],
    name="test_celu_bfloat16",
)
```

```{toctree}
text_diff_Celu_12_28
```

(l-onnx-op-celu-12)=

## Celu - 12

### Version

- **name**: [Celu (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Celu)
- **domain**: `main`
- **since_version**: `12`
- **function**: `True`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 12**.

### Summary

Continuously Differentiable Exponential Linear Units:
Perform the linear unit element-wise on the input tensor X
using formula:

```
max(0,x) + min(0,alpha*(exp(x/alpha)-1))
```

### Attributes

* **alpha - FLOAT** (default is `1.0`):

  The Alpha value in Celu formula which control the shape of the unit. The default value is 1.0.

### Inputs

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

  Input tensor

### Outputs

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

  Output tensor

### Type Constraints

* **T** in ( `tensor(float)` ):

  Constrain input and output types to float32 tensors.