Hardmax - version 11#

This page documents version 11 of operator Hardmax. See Hardmax for the latest version (since version 13).

  • Domain: ai.onnx

  • Since version: 11

The operator computes the hardmax (1 for the first maximum value, and 0 for all others) values for the given input. Inputs are conceptually coerced to a 2D matrix and Hardmax is applied on the second dimension. The output tensor has the same shape as the input tensor.

Inputs

  • input (T): The input tensor that’s coerced into a 2D matrix of size (NxD) as described above.

Outputs

  • output (T): The output values with the same shape as input tensor (the original size without coercion).

Attributes

  • axis (int): Describes the dimension Softmax will be performed on. Negative value means counting dimensions from the back.

Type Constraints

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

Differences with previous version (1)#

SchemaDiff: Hardmax (domain 'ai.onnx')

  • old version: 1

  • new version: 11

  • breaking: no