ReduceL2

ReduceL2 - 18

Version

  • name: ReduceL2 (GitHub)

  • domain: main

  • since_version: 18

  • function: True

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 18.

Summary

Computes the L2 norm of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 0.

The above behavior is similar to numpy, with the exception that numpy defaults keepdims to False instead of True.

Function Body

The function definition for this operator.

<
  domain: "",
  opset_import: ["" : 18]
>
ReduceL2 <noop_with_empty_axes,keepdims>(data, axes) => (reduced)
{
   data_square = Mul (data, data)
   sum_square = ReduceSum <keepdims: int = @keepdims, noop_with_empty_axes: int = @noop_with_empty_axes> (data_square, axes)
   sum_square_dbl = Cast <to: int = 1> (sum_square)
   sqrt = Sqrt (sum_square_dbl)
   reduced = CastLike (sqrt, data)
}

Attributes

  • keepdims - INT (default is '1'):

    Keep the reduced dimension or not, default 1 means keep reduced dimension.

  • noop_with_empty_axes - INT (default is '0'):

    Defines behavior when axes is not provided or is empty. If false (default), reduction happens over all axes. If true, no reduction is applied, but other operations will be performed. For example, ReduceSumSquare acts as a vanilla Square.

Inputs

Between 1 and 2 inputs.

  • data (heterogeneous) - T:

    An input tensor.

  • axes (optional, heterogeneous) - tensor(int64):

    Optional input list of integers, along which to reduce. The default is to reduce over empty axes. When axes is empty (either not provided or explicitly empty), behavior depends on ‘noop_with_empty_axes’: reduction over all axes if ‘noop_with_empty_axes’ is false, or no reduction is applied if ‘noop_with_empty_axes’ is true (but other operations will be performed). Accepted range is [-r, r-1] where r = rank(data).

Outputs

  • reduced (heterogeneous) - T:

    Reduced output tensor.

Type Constraints

  • T in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ):

    Constrain input and output types to numeric tensors.

ReduceL2 - 13

Version

  • name: ReduceL2 (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

Computes the L2 norm of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 0.

The above behavior is similar to numpy, with the exception that numpy defaults keepdims to False instead of True.

Attributes

  • axes - INTS :

    A list of integers, along which to reduce. The default is to reduce over all the dimensions of the input tensor. Accepted range is [-r, r-1] where r = rank(data).

  • keepdims - INT (default is '1'):

    Keep the reduced dimension or not, default 1 means keep reduced dimension.

Inputs

  • data (heterogeneous) - T:

    An input tensor.

Outputs

  • reduced (heterogeneous) - T:

    Reduced output tensor.

Type Constraints

  • T in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ):

    Constrain input and output types to numeric tensors.

ReduceL2 - 11

Version

  • name: ReduceL2 (GitHub)

  • domain: main

  • since_version: 11

  • function: False

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 11.

Summary

Computes the L2 norm of the input tensor’s element along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equal 0, then the resulted tensor have the reduced dimension pruned.

The above behavior is similar to numpy, with the exception that numpy defaults keepdims to False instead of True.

Attributes

  • axes - INTS :

    A list of integers, along which to reduce. The default is to reduce over all the dimensions of the input tensor. Accepted range is [-r, r-1] where r = rank(data).

  • keepdims - INT (default is '1'):

    Keep the reduced dimension or not, default 1 means keep reduced dimension.

Inputs

  • data (heterogeneous) - T:

    An input tensor.

Outputs

  • reduced (heterogeneous) - T:

    Reduced output tensor.

Type Constraints

  • T in ( tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ):

    Constrain input and output types to high-precision numeric tensors.

ReduceL2 - 1

Version

  • name: ReduceL2 (GitHub)

  • domain: main

  • since_version: 1

  • function: False

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 1.

Summary

Computes the L2 norm of the input tensor’s element along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equal 0, then the resulted tensor have the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 0.

The above behavior is similar to numpy, with the exception that numpy defaults keepdims to False instead of True.

Attributes

  • axes - INTS :

    A list of integers, along which to reduce. The default is to reduce over all the dimensions of the input tensor.

  • keepdims - INT (default is '1'):

    Keep the reduced dimension or not, default 1 means keep reduced dimension.

Inputs

  • data (heterogeneous) - T:

    An input tensor.

Outputs

  • reduced (heterogeneous) - T:

    Reduced output tensor.

Type Constraints

  • T in ( tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ):

    Constrain input and output types to high-precision numeric tensors.