Enable zero epsilon attribute in BatchNormInference operation (#5657)

This commit is contained in:
Gabriele Galiero Casay
2021-05-18 06:30:10 +02:00
committed by GitHub
parent e41e25533d
commit 6a8f8a0761
6 changed files with 21 additions and 28 deletions

View File

@@ -58,7 +58,7 @@ For a particular activation, consider a mini-batch \f$\mathcal{B}\f$ of m values
* *epsilon*
* **Description**: *epsilon* is a constant added to the variance for numerical stability.
* **Range of values**: a positive floating-point number
* **Range of values**: a floating-point number greater than or equal to zero
* **Type**: `float`
* **Default value**: none
* **Required**: *yes*

View File

@@ -58,7 +58,7 @@ For a particular activation, consider a mini-batch \f$\mathcal{B}\f$ of m values
* *epsilon*
* **Description**: *epsilon* is a constant added to the variance for numerical stability.
* **Range of values**: a positive floating-point number
* **Range of values**: a floating-point number greater than or equal to zero
* **Type**: `float`
* **Default value**: none
* **Required**: *yes*