Elu

Elu - 6

Version

• name: Elu (GitHub)

• domain: main

• since_version: 6

• function: True

• support_level: SupportType.COMMON

• shape inference: True

This version of the operator has been available since version 6.

Summary

Elu takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the function f(x) = alpha * (exp(x) - 1.) for x < 0, f(x) = x for x >= 0., is applied to the tensor elementwise.

Attributes

• alpha: Coefficient of ELU. Default value is 1.0.

Inputs

• X (heterogeneous) - T: 1D input tensor

Outputs

• Y (heterogeneous) - T: 1D output tensor

Type Constraints

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

Examples

default

node = onnx.helper.make_node("Elu", inputs=["x"], outputs=["y"], alpha=2.0)

x = np.array([-1, 0, 1]).astype(np.float32)
# expected output [-1.2642411, 0., 1.]
y = np.clip(x, 0, np.inf) + (np.exp(np.clip(x, -np.inf, 0)) - 1) * 2.0
expect(node, inputs=[x], outputs=[y], name="test_elu_example")

x = np.random.randn(3, 4, 5).astype(np.float32)
y = np.clip(x, 0, np.inf) + (np.exp(np.clip(x, -np.inf, 0)) - 1) * 2.0
expect(node, inputs=[x], outputs=[y], name="test_elu")

_elu_default

default_alpha = 1.0
node = onnx.helper.make_node(
    "Elu",
    inputs=["x"],
    outputs=["y"],
)
x = np.random.randn(3, 4, 5).astype(np.float32)
y = np.clip(x, 0, np.inf) + (np.exp(np.clip(x, -np.inf, 0)) - 1) * default_alpha
expect(node, inputs=[x], outputs=[y], name="test_elu_default")

Differences

0	0	Elu takes one input data (Tensor) and produces one output data	Elu takes one input data (Tensor) and produces one output data
1	1	(Tensor) where the function f(x) = alpha * (exp(x) - 1.) for x <	(Tensor) where the function f(x) = alpha * (exp(x) - 1.) for x <
2	2	0, f(x) = x for x >= 0., is applied to the tensor elementwise.	0, f(x) = x for x >= 0., is applied to the tensor elementwise.
3	3
4	4	**Attributes**	**Attributes**
5	5
6	6	* **alpha**:	* **alpha**:
7	7	Coefficient of ELU default to 1.0. Default value is 1.0.	Coefficient of ELU. Default value is 1.0.
8		* **consumed_inputs**:
9		legacy optimization attribute.
10	8
11	9	**Inputs**	**Inputs**
12	10
13	11	* **X** (heterogeneous) - **T**:	* **X** (heterogeneous) - **T**:
14	12	1D input tensor	1D input tensor
15	13
16	14	**Outputs**	**Outputs**
17	15
18	16	* **Y** (heterogeneous) - **T**:	* **Y** (heterogeneous) - **T**:
19	17	1D input tensor	1D output tensor
20	18
21	19	**Type Constraints**	**Type Constraints**
22	20
23	21	* **T** in (	* **T** in (
24	22	tensor(double),	tensor(double),
25	23	tensor(float),	tensor(float),
26	24	tensor(float16)	tensor(float16)
27	25	):	):
28	26	Constrain input and output types to float tensors.	Constrain input and output types to float tensors.

Elu - 1

Version

• name: Elu (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

Elu takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the function f(x) = alpha * (exp(x) - 1.) for x < 0, f(x) = x for x >= 0., is applied to the tensor elementwise.

Attributes

• alpha: Coefficient of ELU default to 1.0. Default value is 1.0.

• consumed_inputs: legacy optimization attribute.

Inputs

• X (heterogeneous) - T: 1D input tensor

Outputs

• Y (heterogeneous) - T: 1D input tensor

Type Constraints

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