LeakyRelu - version 1#

This page documents version 1 of operator LeakyRelu. See LeakyRelu for the latest version (since version 16).

  • Domain: ai.onnx

  • Since version: 1

LeakyRelu takes input data (Tensor ) and an argument alpha, and produces one output data (Tensor ) where the function f(x) = alpha * x for x  = 0, is applied to the data tensor elementwise.

Inputs

  • X (T): Input tensor

Outputs

  • Y (T): Output tensor

Attributes

  • alpha (float): Coefficient of leakage default to 0.01.

Type Constraints

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