Selu

Selu - 6

Version

• name: Selu (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

Selu takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the scaled exponential linear unit function, y = gamma * (alpha * e^x - alpha) for x <= 0, y = gamma * x for x > 0, is applied to the tensor elementwise.

Attributes

• alpha: Coefficient of SELU default to 1.67326319217681884765625 (i.e., float32 approximation of 1.6732632423543772848170429916717). Default value is 1.6732631921768188.

• gamma: Coefficient of SELU default to 1.05070102214813232421875 (i.e., float32 approximation of 1.0507009873554804934193349852946). Default value is 1.0507010221481323.

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.

Examples

default

node = onnx.helper.make_node(
    "Selu", inputs=["x"], outputs=["y"], alpha=2.0, gamma=3.0
)

x = np.array([-1, 0, 1]).astype(np.float32)
# expected output [-3.79272318, 0., 3.]
y = (
    np.clip(x, 0, np.inf) * 3.0
    + (np.exp(np.clip(x, -np.inf, 0)) - 1) * 2.0 * 3.0
)
expect(node, inputs=[x], outputs=[y], name="test_selu_example")

x = np.random.randn(3, 4, 5).astype(np.float32)
y = (
    np.clip(x, 0, np.inf) * 3.0
    + (np.exp(np.clip(x, -np.inf, 0)) - 1) * 2.0 * 3.0
)
expect(node, inputs=[x], outputs=[y], name="test_selu")

_selu_default

default_alpha = 1.67326319217681884765625
default_gamma = 1.05070102214813232421875
node = onnx.helper.make_node(
    "Selu",
    inputs=["x"],
    outputs=["y"],
)
x = np.random.randn(3, 4, 5).astype(np.float32)
y = (
    np.clip(x, 0, np.inf) * default_gamma
    + (np.exp(np.clip(x, -np.inf, 0)) - 1) * default_alpha * default_gamma
)
expect(node, inputs=[x], outputs=[y], name="test_selu_default")

Differences

0	0	Selu takes one input data (Tensor) and produces one output data	Selu takes one input data (Tensor) and produces one output data
1	1	(Tensor) where the scaled exponential linear unit function,	(Tensor) where the scaled exponential linear unit function,
2	2	y = gamma * (alpha * e^x - alpha) for x <= 0, y = gamma * x for x > 0,	y = gamma * (alpha * e^x - alpha) for x <= 0, y = gamma * x for x > 0,
3	3	is applied to the tensor elementwise.	is applied to the tensor elementwise.
4	4
5	5	**Attributes**	**Attributes**
6	6
7	7	* **alpha**:	* **alpha**:
8	8	Coefficient of SELU default to 1.6732. Default value is 1.673200011253357.	Coefficient of SELU default to 1.67326319217681884765625 (i.e.,
9	9	* **consumed_inputs**:	float32 approximation of 1.6732632423543772848170429916717). Default value is 1.6732631921768188.
	10		* **gamma**:
10	11	legacy optimization attribute.	Coefficient of SELU default to 1.05070102214813232421875 (i.e.,
11	12	* **gamma**:	float32 approximation of 1.0507009873554804934193349852946). Default value is 1.0507010221481323.
12		Coefficient of SELU default to 1.0507. Default value is 1.0506999492645264.
13	13
14	14	**Inputs**	**Inputs**
15	15
16	16	* **X** (heterogeneous) - **T**:	* **X** (heterogeneous) - **T**:
17	17	Input tensor	Input tensor
18	18
19	19	**Outputs**	**Outputs**
20	20
21	21	* **Y** (heterogeneous) - **T**:	* **Y** (heterogeneous) - **T**:
22	22	Output tensor	Output tensor
23	23
24	24	**Type Constraints**	**Type Constraints**
25	25
26	26	* **T** in (	* **T** in (
27	27	tensor(double),	tensor(double),
28	28	tensor(float),	tensor(float),
29	29	tensor(float16)	tensor(float16)
30	30	):	):
31	31	Constrain input and output types to float tensors.	Constrain input and output types to float tensors.

Selu - 1

Version

• name: Selu (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

Selu takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the scaled exponential linear unit function, y = gamma * (alpha * e^x - alpha) for x <= 0, y = gamma * x for x > 0, is applied to the tensor elementwise.

Attributes

• alpha: Coefficient of SELU default to 1.6732. Default value is 1.673200011253357.

• consumed_inputs: legacy optimization attribute.

• gamma: Coefficient of SELU default to 1.0507. Default value is 1.0506999492645264.

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.