ConstantOfShape - version 21#

This page documents version 21 of operator ConstantOfShape. See ConstantOfShape for the latest version (since version 25).

Generate a tensor with given value and shape.

Inputs

input (T1): 1D tensor. The shape of the expected output tensor. If empty tensor is given, the output would be a scalar. All values must be >= 0.

Outputs

output (T2): Output tensor of shape specified by ‘input’.If attribute ‘value’ is specified, the value and datatype of the output tensor is taken from ‘value’.If attribute ‘value’ is not specified, the value in the output defaults to 0, and the datatype defaults to float32.

Attributes

value (tensor): (Optional) The value of the output elements.Should be a one-element tensor. If not specified, it defaults to a tensor of value 0 and datatype float32

Type Constraints

T1: Constrain input types. Allowed types: tensor(int64).
T2: Constrain output types to be numerics or boolean. Allowed types: tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(float8e4m3fn), tensor(float8e4m3fnuz), tensor(float8e5m2), tensor(float8e5m2fnuz), tensor(int16), tensor(int32), tensor(int4), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint4), tensor(uint64), tensor(uint8).

Differences with previous version (20)#

SchemaDiff: ConstantOfShape (domain 'ai.onnx')

Type constraints: