(l-onnx-doc-Mean)=

# Mean


(l-onnx-op-mean-13)=

## Mean - 13

### Version

- **name**: [Mean (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Mean)
- **domain**: `main`
- **since_version**: `13`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 13**.

### Summary

Element-wise mean of each of the input tensors (with Numpy-style broadcasting support).
All inputs and outputs must have the same data type.
This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).

### Inputs

Between 1 and 2147483647 inputs.

- **data_0** (variadic, heterogeneous) - **T**:

  List of tensors for mean.

### Outputs

- **mean** (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

data_0 = np.array([3, 0, 2]).astype(np.float32)
data_1 = np.array([1, 3, 4]).astype(np.float32)
data_2 = np.array([2, 6, 6]).astype(np.float32)
result = np.array([2, 3, 4]).astype(np.float32)
node = onnx.helper.make_node(
    "Mean",
    inputs=["data_0", "data_1", "data_2"],
    outputs=["result"],
)
expect(
    node,
    inputs=[data_0, data_1, data_2],
    outputs=[result],
    name="test_mean_example",
)

node = onnx.helper.make_node(
    "Mean",
    inputs=["data_0"],
    outputs=["result"],
)
expect(node, inputs=[data_0], outputs=[data_0], name="test_mean_one_input")

result = np.divide(np.add(data_0, data_1), 2.0)
node = onnx.helper.make_node(
    "Mean",
    inputs=["data_0", "data_1"],
    outputs=["result"],
)
expect(
    node, inputs=[data_0, data_1], outputs=[result], name="test_mean_two_inputs"
)
```

```{toctree}
text_diff_Mean_8_13
```

(l-onnx-op-mean-8)=

## Mean - 8

### Version

- **name**: [Mean (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Mean)
- **domain**: `main`
- **since_version**: `8`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 8**.

### Summary

Element-wise mean of each of the input tensors (with Numpy-style broadcasting support).
All inputs and outputs must have the same data type.
This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).

### Inputs

Between 1 and 2147483647 inputs.

- **data_0** (variadic, heterogeneous) - **T**:

  List of tensors for mean.

### Outputs

- **mean** (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_Mean_6_13
text_diff_Mean_6_8
```

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

## Mean - 6

### Version

- **name**: [Mean (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Mean)
- **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

Element-wise mean of each of the input tensors. All inputs and outputs must
have the same shape and data type.

### Inputs

Between 1 and 2147483647 inputs.

- **data_0** (variadic, heterogeneous) - **T**:

  List of tensors for Mean.

### Outputs

- **mean** (heterogeneous) - **T**:

  Output tensor. Same dimension as inputs.

### Type Constraints

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

  Constrain input and output types to float tensors.

```{toctree}
text_diff_Mean_1_13
text_diff_Mean_1_8
text_diff_Mean_1_6
```

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

## Mean - 1

### Version

- **name**: [Mean (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Mean)
- **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

Element-wise mean of each of the input tensors. All inputs and outputs must
have the same shape and data type.

### Attributes

* **consumed_inputs - INTS** :

  legacy optimization attribute.

### Inputs

Between 1 and 2147483647 inputs.

- **data_0** (variadic, heterogeneous) - **T**:

  List of tensors for Mean.

### Outputs

- **mean** (heterogeneous) - **T**:

  Output tensor. Same dimension as inputs.

### Type Constraints

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

  Constrain input and output types to float tensors.