HardSigmoid#

Domain: ai.onnx
Since version: 22

HardSigmoid takes one input data (Tensor ) and produces one output data (Tensor ) where the HardSigmoid function, y = max(0, min(1, alpha * x + beta)), is applied to the tensor elementwise.

Inputs

X (T): Input tensor

Outputs

Y (T): Output tensor

Attributes

alpha (float): Value of alpha.
beta (float): Value of beta.

Type Constraints

T: Constrain input and output types to float tensors. Allowed types: tensor(bfloat16), tensor(double), tensor(float), tensor(float16).

Examples#

test_cc_hardsigmoid

Node:
  HardSigmoid(X) -> (Y)
  Attributes:
    alpha = 0.5
    beta = 0.6000000238418579

Inputs:
  X: shape=(2, 3), dtype=float32
    [[-3. , -1. , -0.5],
     [ 0.5,  1. ,  3. ]]

Outputs:
  Y: shape=(2, 3), dtype=float32
    [[0.        , 0.10000002, 0.35000002],
     [0.85      , 1.        , 1.        ]]

test_cc_hardsigmoid_default

Node:
  HardSigmoid(X) -> (Y)

Inputs:
  X: shape=(2, 3), dtype=float32
    [[-3. , -1. , -0.5],
     [ 0.5,  1. ,  3. ]]

Outputs:
  Y: shape=(2, 3), dtype=float32
    [[0. , 0.3, 0.4],
     [0.6, 0.7, 1. ]]

test_cc_hardsigmoid_example

Node:
  HardSigmoid(X) -> (Y)
  Attributes:
    alpha = 0.5
    beta = 0.6000000238418579

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

Outputs:
  Y: shape=(3,), dtype=float32
    [0.10000002, 0.6       , 1.        ]

Differences with previous version (6)#

SchemaDiff: HardSigmoid (domain 'ai.onnx')

old version: 6
new version: 22
breaking: no

Type constraints:

changed ‘T’: added types: [‘tensor(bfloat16)’]

HardSigmoid#

Examples#

Differences with previous version (6)#

Version History#