Exp

Exp - 13

Version

• name: Exp (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

Calculates the exponential of the given input tensor, element-wise.

Inputs

• input (heterogeneous) - T: Input tensor

Outputs

• output (heterogeneous) - T: The exponential of the input tensor computed element-wise

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(
    "Exp",
    inputs=["x"],
    outputs=["y"],
)

x = np.array([-1, 0, 1]).astype(np.float32)
y = np.exp(x)  # expected output [0.36787945, 1., 2.71828175]
expect(node, inputs=[x], outputs=[y], name="test_exp_example")

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

Differences

0	0	Calculates the exponential of the given input tensor, element-wise.	Calculates the exponential of the given input tensor, element-wise.
1	1
2	2	**Inputs**	**Inputs**
3	3
4	4	* **input** (heterogeneous) - **T**:	* **input** (heterogeneous) - **T**:
5	5	Input tensor	Input tensor
6	6
7	7	**Outputs**	**Outputs**
8	8
9	9	* **output** (heterogeneous) - **T**:	* **output** (heterogeneous) - **T**:
10	10	The exponential of the input tensor computed element-wise	The exponential of the input tensor computed element-wise
11	11
12	12	**Type Constraints**	**Type Constraints**
13	13
14	14	* **T** in (	* **T** in (
	15		tensor(bfloat16),
15	16	tensor(double),	tensor(double),
16	17	tensor(float),	tensor(float),
17	18	tensor(float16)	tensor(float16)
18	19	):	):
19	20	Constrain input and output types to float tensors.	Constrain input and output types to float tensors.

Exp - 6

Version

• name: Exp (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

Calculates the exponential of the given input tensor, element-wise.

Inputs

• input (heterogeneous) - T: Input tensor

Outputs

• output (heterogeneous) - T: The exponential of the input tensor computed element-wise

Type Constraints

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

Differences

0	0	Calculates the exponential of the given input tensor, element-wise.	Calculates the exponential of the given input tensor, element-wise.
1	1
2		**Attributes**
3
4		* **consumed_inputs**:
5		legacy optimization attribute.
6
7	2	**Inputs**	**Inputs**
8	3
9	4	* **input** (heterogeneous) - **T**:	* **input** (heterogeneous) - **T**:
10	5	Input tensor	Input tensor
11	6
12	7	**Outputs**	**Outputs**
13	8
14	9	* **output** (heterogeneous) - **T**:	* **output** (heterogeneous) - **T**:
15	10	The exponential of the input tensor computed element-wise	The exponential of the input tensor computed element-wise
16	11
17	12	**Type Constraints**	**Type Constraints**
18	13
19	14	* **T** in (	* **T** in (
20	15	tensor(double),	tensor(double),
21	16	tensor(float),	tensor(float),
22	17	tensor(float16)	tensor(float16)
23	18	):	):
24	19	Constrain input and output types to float tensors.	Constrain input and output types to float tensors.

Exp - 1

Version

• name: Exp (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

Calculates the exponential of the given input tensor, element-wise.

Attributes

• consumed_inputs: legacy optimization attribute.

Inputs

• input (heterogeneous) - T: Input tensor

Outputs

• output (heterogeneous) - T: The exponential of the input tensor computed element-wise

Type Constraints

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