Tanh#

Tanh - 13#

Version

  • name: Tanh (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 hyperbolic tangent of the given input tensor element-wise.

Inputs

  • input (heterogeneous) - T: Input tensor

Outputs

  • output (heterogeneous) - T: The hyperbolic tangent values 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(
    "Tanh",
    inputs=["x"],
    outputs=["y"],
)

x = np.array([-1, 0, 1]).astype(np.float32)
y = np.tanh(x)  # expected output [-0.76159418, 0., 0.76159418]
expect(node, inputs=[x], outputs=[y], name="test_tanh_example")

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

Differences

00Calculates the hyperbolic tangent of the given input tensor element-wise.Calculates the hyperbolic tangent of the given input tensor element-wise.
11
22**Inputs****Inputs**
33
44* **input** (heterogeneous) - **T**:* **input** (heterogeneous) - **T**:
55 Input tensor Input tensor
66
77**Outputs****Outputs**
88
99* **output** (heterogeneous) - **T**:* **output** (heterogeneous) - **T**:
1010 The hyperbolic tangent values of the input tensor computed element- The hyperbolic tangent values of the input tensor computed element-
1111 wise wise
1212
1313**Type Constraints****Type Constraints**
1414
1515* **T** in (* **T** in (
16 tensor(bfloat16),
1617 tensor(double), tensor(double),
1718 tensor(float), tensor(float),
1819 tensor(float16) tensor(float16)
1920 ): ):
2021 Constrain input and output types to float tensors. Constrain input and output types to float tensors.

Tanh - 6#

Version

  • name: Tanh (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 hyperbolic tangent of the given input tensor element-wise.

Inputs

  • input (heterogeneous) - T: Input tensor

Outputs

  • output (heterogeneous) - T: The hyperbolic tangent values 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

00Calculates the hyperbolic tangent of the given input tensor element-wise.Calculates the hyperbolic tangent of the given input tensor element-wise.
11
2**Attributes**
3
4* **consumed_inputs**:
5 legacy optimization attribute.
6
72**Inputs****Inputs**
83
94* **input** (heterogeneous) - **T**:* **input** (heterogeneous) - **T**:
105 1-D input tensor Input tensor
116
127**Outputs****Outputs**
138
149* **output** (heterogeneous) - **T**:* **output** (heterogeneous) - **T**:
1510 The hyperbolic tangent values of the input tensor computed element- The hyperbolic tangent values of the input tensor computed element-
1611 wise wise
1712
1813**Type Constraints****Type Constraints**
1914
2015* **T** in (* **T** in (
2116 tensor(double), tensor(double),
2217 tensor(float), tensor(float),
2318 tensor(float16) tensor(float16)
2419 ): ):
2520 Constrain input and output types to float tensors. Constrain input and output types to float tensors.

Tanh - 1#

Version

  • name: Tanh (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 hyperbolic tangent of the given input tensor element-wise.

Attributes

  • consumed_inputs: legacy optimization attribute.

Inputs

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

Outputs

  • output (heterogeneous) - T: The hyperbolic tangent values 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.