(l-onnx-doc-Min)=

# Min


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

## Min - 13

### Version

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

### Outputs

- **min** (heterogeneous) - **T**:

  Output tensor.

### Type Constraints

* **T** in ( `tensor(bfloat16)`, `tensor(double)`, `tensor(float)`, `tensor(float16)`, `tensor(int16)`, `tensor(int32)`, `tensor(int64)`, `tensor(int8)`, `tensor(uint16)`, `tensor(uint32)`, `tensor(uint64)`, `tensor(uint8)` ):

  Constrain input and output types to numeric tensors.

### Examples

#### default

```python
import numpy as np
import onnx

data_0 = np.array([3, 2, 1]).astype(np.float32)
data_1 = np.array([1, 4, 4]).astype(np.float32)
data_2 = np.array([2, 5, 0]).astype(np.float32)
result = np.array([1, 2, 0]).astype(np.float32)
node = onnx.helper.make_node(
    "Min",
    inputs=["data_0", "data_1", "data_2"],
    outputs=["result"],
)
expect(
    node,
    inputs=[data_0, data_1, data_2],
    outputs=[result],
    name="test_min_example",
)

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

result = np.minimum(data_0, data_1)
node = onnx.helper.make_node(
    "Min",
    inputs=["data_0", "data_1"],
    outputs=["result"],
)
expect(
    node, inputs=[data_0, data_1], outputs=[result], name="test_min_two_inputs"
)
```

#### _min_all_numeric_types

```python
import numpy as np
import onnx

for op_dtype in all_numeric_dtypes:
    data_0 = np.array([3, 2, 1]).astype(op_dtype)
    data_1 = np.array([1, 4, 4]).astype(op_dtype)
    result = np.array([1, 2, 1]).astype(op_dtype)
    node = onnx.helper.make_node(
        "Min",
        inputs=["data_0", "data_1"],
        outputs=["result"],
    )
    expect(
        node,
        inputs=[data_0, data_1],
        outputs=[result],
        name=f"test_min_{np.dtype(op_dtype).name}",
    )
```

```{toctree}
text_diff_Min_12_13
```

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

## Min - 12

### Version

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

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

### Summary

Element-wise min 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 min.

### Outputs

- **min** (heterogeneous) - **T**:

  Output tensor.

### Type Constraints

* **T** in ( `tensor(double)`, `tensor(float)`, `tensor(float16)`, `tensor(int16)`, `tensor(int32)`, `tensor(int64)`, `tensor(int8)`, `tensor(uint16)`, `tensor(uint32)`, `tensor(uint64)`, `tensor(uint8)` ):

  Constrain input and output types to numeric tensors.

```{toctree}
text_diff_Min_8_13
text_diff_Min_8_12
```

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

## Min - 8

### Version

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

### Outputs

- **min** (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_Min_6_13
text_diff_Min_6_12
text_diff_Min_6_8
```

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

## Min - 6

### Version

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

### Outputs

- **min** (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_Min_1_13
text_diff_Min_1_12
text_diff_Min_1_8
text_diff_Min_1_6
```

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

## Min - 1

### Version

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

### Outputs

- **min** (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.