ReduceMax - version 13#

This page documents version 13 of operator ReduceMax. See ReduceMax for the latest version (since version 20).

  • Domain: ai.onnx

  • Since version: 13

Computes the max 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. The axes attribute specifies which dimensions to reduce. Negative axes are supported. If axes is not provided, all dimensions are reduced. Reduction over an empty set of values yields minus infinity (if supported by the datatype) or the minimum value of the data type otherwise.

Inputs

  • data (T): An input tensor.

Outputs

  • reduced (T): Reduced output tensor.

Attributes

  • axes (int[]): 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): Keep the reduced dimension or not, default 1 means keep reduced dimension.

Type Constraints

  • T: Constrain input and output types to high-precision and 8 bit numeric tensors. Allowed types: tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(int8), tensor(uint32), tensor(uint64), tensor(uint8).

Differences with previous version (12)#

SchemaDiff: ReduceMax (domain 'ai.onnx')

  • old version: 12

  • new version: 13

  • breaking: no

Type constraints:

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