Celu - version 12#

This page documents version 12 of operator Celu. See Celu for the latest version (since version 28).

Domain: ai.onnx
Since version: 12

Continuously Differentiable Exponential Linear Units: Perform the linear unit element-wise on the input tensor X using formula:

max(0,x) + min(0,alpha*(exp(x/alpha)-1))

Inputs

X (T): Input tensor

Outputs

Y (T): Output tensor

Attributes

alpha (float): The Alpha value in Celu formula which control the shape of the unit. The default value is 1.0.

Type Constraints

T: Constrain input and output types to float32 tensors. Allowed types: tensor(float).

Examples#

test_cc_celu

Node:
  Celu(X) -> (Y)
  Attributes:
    alpha = 2.0

Inputs:
  X: shape=(2, 3), dtype=float32
    [[-3., -1.,  0.],
     [ 1.,  2.,  3.]]

Outputs:
  Y: shape=(2, 3), dtype=float32
    [[-1.5537397 , -0.78693867,  0.        ],
     [ 1.        ,  2.        ,  3.        ]]

test_cc_celu_default

Node:
  Celu(X) -> (Y)

Inputs:
  X: shape=(2, 3), dtype=float32
    [[-3., -1.,  0.],
     [ 1.,  2.,  3.]]

Outputs:
  Y: shape=(2, 3), dtype=float32
    [[-0.95021296, -0.63212055,  0.        ],
     [ 1.        ,  2.        ,  3.        ]]