Sqrt

Sqrt - 13

Version

• name: Sqrt (GitHub)

• 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

Square root takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the square root is, y = x^0.5, is applied to the tensor elementwise. If x is negative, then it will return NaN.

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

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

x = np.array([1, 4, 9]).astype(np.float32)
y = np.sqrt(x)  # expected output [1., 2., 3.]
expect(node, inputs=[x], outputs=[y], name="test_sqrt_example")

x = np.abs(np.random.randn(3, 4, 5).astype(np.float32))
y = np.sqrt(x)
expect(node, inputs=[x], outputs=[y], name="test_sqrt")

Differences

0	0	Square root takes one input data (Tensor) and produces one output data	Square root takes one input data (Tensor) and produces one output data
1	1	(Tensor) where the square root is, y = x^0.5, is applied to	(Tensor) where the square root is, y = x^0.5, is applied to
2	2	the tensor elementwise. If x is negative, then it will return NaN.	the tensor elementwise. If x is negative, then it will return NaN.
3	3
4	4	**Inputs**	**Inputs**
5	5
6	6	* **X** (heterogeneous) - **T**:	* **X** (heterogeneous) - **T**:
7	7	Input tensor	Input tensor
8	8
9	9	**Outputs**	**Outputs**
10	10
11	11	* **Y** (heterogeneous) - **T**:	* **Y** (heterogeneous) - **T**:
12	12	Output tensor	Output tensor
13	13
14	14	**Type Constraints**	**Type Constraints**
15	15
16	16	* **T** in (	* **T** in (
	17		tensor(bfloat16),
17	18	tensor(double),	tensor(double),
18	19	tensor(float),	tensor(float),
19	20	tensor(float16)	tensor(float16)
20	21	):	):
21	22	Constrain input and output types to float tensors.	Constrain input and output types to float tensors.

Sqrt - 6

Version

• name: Sqrt (GitHub)

• 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

Square root takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the square root is, y = x^0.5, is applied to the tensor elementwise. If x is negative, then it will return NaN.

Inputs

• X (heterogeneous) - T: Input tensor

Outputs

• Y (heterogeneous) - T: Output tensor

Type Constraints

• T in ( tensor(double), tensor(float), tensor(float16) ): Constrain input and output types to float tensors.

Differences

0	0	Square root takes one input data (Tensor) and produces one output data	Square root takes one input data (Tensor) and produces one output data
1	1	(Tensor) where the square root is, y = x^0.5, is applied to	(Tensor) where the square root is, y = x^0.5, is applied to
2	2	the tensor elementwise. If x is negative, then it will return NaN.	the tensor elementwise. If x is negative, then it will return NaN.
3	3
4		**Attributes**
5
6		* **consumed_inputs**:
7		legacy optimization attribute.
8
9	4	**Inputs**	**Inputs**
10	5
11	6	* **X** (heterogeneous) - **T**:	* **X** (heterogeneous) - **T**:
12	7	Input tensor	Input tensor
13	8
14	9	**Outputs**	**Outputs**
15	10
16	11	* **Y** (heterogeneous) - **T**:	* **Y** (heterogeneous) - **T**:
17	12	Output tensor	Output tensor
18	13
19	14	**Type Constraints**	**Type Constraints**
20	15
21	16	* **T** in (	* **T** in (
22	17	tensor(double),	tensor(double),
23	18	tensor(float),	tensor(float),
24	19	tensor(float16)	tensor(float16)
25	20	):	):
26	21	Constrain input and output types to float tensors.	Constrain input and output types to float tensors.

Sqrt - 1

Version

• name: Sqrt (GitHub)

• 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

Square root takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the square root is, y = x^0.5, is applied to the tensor elementwise. If x is negative, then it will return NaN.

Attributes

• consumed_inputs: legacy optimization attribute.

Inputs

• X (heterogeneous) - T: Input tensor

Outputs

• Y (heterogeneous) - T: Output tensor

Type Constraints

• T in ( tensor(double), tensor(float), tensor(float16) ): Constrain input and output types to float tensors.