Softplus¶

Softplus - 22¶

Version¶

name: Softplus (GitHub)
domain: main
since_version: 22
function: True
support_level: SupportType.COMMON
shape inference: True

This version of the operator has been available since version 22.

Summary¶

Softplus takes one input data (Tensor<T>) and produces one output data (Tensor<T>) where the softplus function, y = ln(exp(x) + 1), is applied to the tensor elementwise.

Function Body¶

The function definition for this operator.

&lt;
  domain: &#34;&#34;,
  opset_import: [&#34;&#34; : 18]
&gt;
Softplus (X) =&gt; (Y)
{
   exp_x = Exp (X)
   one = Constant &lt;value: tensor = float {1}&gt; ()
   one_cast = CastLike (one, X)
   exp_x_add_one = Add (exp_x, one_cast)
   Y = Log (exp_x_add_one)
}

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¶

import numpy as np
import onnx

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

x = np.array([-1, 0, 1]).astype(np.float32)
y = np.log(
    np.exp(x) + 1
)  # expected output [0.31326166, 0.69314718, 1.31326163]
expect(node, inputs=[x], outputs=[y], name="test_softplus_example")

x = np.random.randn(3, 4, 5).astype(np.float32)
y = np.log(np.exp(x) + 1)
expect(node, inputs=[x], outputs=[y], name="test_softplus")

Softplus - 1 vs 22

Softplus - 1¶