(l-onnx-doc-Clip)=

# Clip


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

## Clip - 13

### Version

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

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

### Summary

Clip operator limits the given input within an interval. The interval is
specified by the inputs 'min' and 'max'. They default to
numeric_limits::lowest() and numeric_limits::max(), respectively.
When 'min' is greater than 'max', the clip operator sets all the 'input' values to
the value of 'max'. Thus, this is equivalent to 'Min(max, Max(input, min))'.

### Inputs

Between 1 and 3 inputs.

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

  Input tensor whose elements to be clipped
- **min** (optional, heterogeneous) - **T**:

  Minimum value, under which element is replaced by min. It must be a scalar(tensor of empty shape).
- **max** (optional, heterogeneous) - **T**:

  Maximum value, above which element is replaced by max. It must be a scalar(tensor of empty shape).

### Outputs

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

  Output tensor with clipped input elements

### 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 all numeric tensors.

### Examples

#### default

```python
import numpy as np
import onnx

node = onnx.helper.make_node(
    "Clip",
    inputs=["x", "min", "max"],
    outputs=["y"],
)

x = np.array([-2, 0, 2]).astype(np.float32)
min_val = np.float32(-1)
max_val = np.float32(1)
y = np.clip(x, min_val, max_val)  # expected output [-1., 0., 1.]
expect(
    node, inputs=[x, min_val, max_val], outputs=[y], name="test_clip_example"
)

x = np.random.randn(3, 4, 5).astype(np.float32)
y = np.clip(x, min_val, max_val)
expect(node, inputs=[x, min_val, max_val], outputs=[y], name="test_clip")
node = onnx.helper.make_node(
    "Clip",
    inputs=["x", "min", "max"],
    outputs=["y"],
)

min_val = np.float32(-5)
max_val = np.float32(5)

x = np.array([-1, 0, 1]).astype(np.float32)
y = np.array([-1, 0, 1]).astype(np.float32)
expect(
    node, inputs=[x, min_val, max_val], outputs=[y], name="test_clip_inbounds"
)

x = np.array([-6, 0, 6]).astype(np.float32)
y = np.array([-5, 0, 5]).astype(np.float32)
expect(
    node, inputs=[x, min_val, max_val], outputs=[y], name="test_clip_outbounds"
)

x = np.array([-1, 0, 6]).astype(np.float32)
y = np.array([-1, 0, 5]).astype(np.float32)
expect(
    node,
    inputs=[x, min_val, max_val],
    outputs=[y],
    name="test_clip_splitbounds",
)

x = np.array([-2, 0, 6]).astype(np.float32)
y = np.array([1, 1, 1]).astype(np.float32)
min_val = np.float32(2)
max_val = np.float32(1)
expect(
    node,
    inputs=[x, min_val, max_val],
    outputs=[y],
    name="test_clip_min_greater_than_max",
)
```

#### _clip_default

```python
import numpy as np
import onnx

node = onnx.helper.make_node(
    "Clip",
    inputs=["x", "min"],
    outputs=["y"],
)
min_val = np.float32(0)
x = np.random.randn(3, 4, 5).astype(np.float32)
y = np.clip(x, min_val, np.inf)
expect(node, inputs=[x, min_val], outputs=[y], name="test_clip_default_min")

no_min = ""  # optional input, not supplied
node = onnx.helper.make_node(
    "Clip",
    inputs=["x", no_min, "max"],
    outputs=["y"],
)
max_val = np.float32(0)
x = np.random.randn(3, 4, 5).astype(np.float32)
y = np.clip(x, -np.inf, max_val)
expect(node, inputs=[x, max_val], outputs=[y], name="test_clip_default_max")

no_max = ""  # optional input, not supplied
node = onnx.helper.make_node(
    "Clip",
    inputs=["x", no_min, no_max],
    outputs=["y"],
)

x = np.array([-1, 0, 1]).astype(np.float32)
y = np.array([-1, 0, 1]).astype(np.float32)
expect(node, inputs=[x], outputs=[y], name="test_clip_default_inbounds")
```

#### _clip_default_int8

```python
import numpy as np
import onnx

node = onnx.helper.make_node(
    "Clip",
    inputs=["x", "min"],
    outputs=["y"],
)
min_val = np.int8(0)
x = np.random.randn(3, 4, 5).astype(np.int8)
y = np.clip(x, min_val, np.iinfo(np.int8).max)
expect(
    node, inputs=[x, min_val], outputs=[y], name="test_clip_default_int8_min"
)

no_min = ""  # optional input, not supplied
node = onnx.helper.make_node(
    "Clip",
    inputs=["x", no_min, "max"],
    outputs=["y"],
)
max_val = np.int8(0)
x = np.random.randn(3, 4, 5).astype(np.int8)
y = np.clip(x, np.iinfo(np.int8).min, max_val)
expect(
    node, inputs=[x, max_val], outputs=[y], name="test_clip_default_int8_max"
)

no_max = ""  # optional input, not supplied
node = onnx.helper.make_node(
    "Clip",
    inputs=["x", no_min, no_max],
    outputs=["y"],
)

x = np.array([-1, 0, 1]).astype(np.int8)
y = np.array([-1, 0, 1]).astype(np.int8)
expect(node, inputs=[x], outputs=[y], name="test_clip_default_int8_inbounds")
```

```{toctree}
text_diff_Clip_12_13
```

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

## Clip - 12

### Version

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

Clip operator limits the given input within an interval. The interval is
specified by the inputs 'min' and 'max'. They default to
numeric_limits::lowest() and numeric_limits::max(), respectively.

### Inputs

Between 1 and 3 inputs.

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

  Input tensor whose elements to be clipped
- **min** (optional, heterogeneous) - **T**:

  Minimum value, under which element is replaced by min. It must be a scalar(tensor of empty shape).
- **max** (optional, heterogeneous) - **T**:

  Maximum value, above which element is replaced by max. It must be a scalar(tensor of empty shape).

### Outputs

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

  Output tensor with clipped input elements

### 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 all numeric tensors.

```{toctree}
text_diff_Clip_11_13
text_diff_Clip_11_12
```

(l-onnx-op-clip-11)=

## Clip - 11

### Version

- **name**: [Clip (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Clip)
- **domain**: `main`
- **since_version**: `11`
- **function**: `False`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 11**.

### Summary

Clip operator limits the given input within an interval. The interval is
specified by the inputs 'min' and 'max'. They default to
numeric_limits::lowest() and numeric_limits::max(), respectively.

### Inputs

Between 1 and 3 inputs.

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

  Input tensor whose elements to be clipped
- **min** (optional, heterogeneous) - **T**:

  Minimum value, under which element is replaced by min. It must be a scalar(tensor of empty shape).
- **max** (optional, heterogeneous) - **T**:

  Maximum value, above which element is replaced by max. It must be a scalar(tensor of empty shape).

### Outputs

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

  Output tensor with clipped input elements

### Type Constraints

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

  Constrain input and output types to float tensors.

```{toctree}
text_diff_Clip_6_13
text_diff_Clip_6_12
text_diff_Clip_6_11
```

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

## Clip - 6

### Version

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

Clip operator limits the given input within an interval. The interval is
specified with arguments 'min' and 'max'. They default to
numeric_limits::lowest() and numeric_limits::max() respectively.

### Attributes

* **max - FLOAT** (default is `(3.402823e+38)`):

  Maximum value, above which element is replaced by max

* **min - FLOAT** (default is `(-3.402823e+38)`):

  Minimum value, under which element is replaced by min

### Inputs

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

  Input tensor whose elements to be clipped

### Outputs

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

  Output tensor with clipped input elements

### Type Constraints

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

  Constrain input and output types to float tensors.

```{toctree}
text_diff_Clip_1_13
text_diff_Clip_1_12
text_diff_Clip_1_11
text_diff_Clip_1_6
```

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

## Clip - 1

### Version

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

Clip operator limits the given input within an interval. The interval is
specified with arguments 'min' and 'max'. They default to
numeric_limits::lowest() and numeric_limits::max() respectively.

### Attributes

* **consumed_inputs - INTS** :

  legacy optimization attribute.

* **max - FLOAT** :

  Maximum value, above which element is replaced by max

* **min - FLOAT** :

  Minimum value, under which element is replaced by min

### Inputs

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

  Input tensor whose elements to be clipped

### Outputs

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

  Output tensor with clipped input elements

### Type Constraints

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

  Constrain input and output types to float tensors.