Gaussian Initializer

A Gaussian initializer is an initializer algorithm to initialize a p-dimensional tensor XR n1 x ... x np with Gaussian random numbers having mean a and standard deviation σ, where a, σR and σ > 0.

Algorithm Parameters

In addition to common parameters of the initializer interface, a Gaussian initializer has the following parameters:

Parameter

Default Value

Description

algorithmFPType

float

The floating-point type that the algorithm uses for intermediate computations. Can be float or double.

method

defaultDense

Performance-oriented computation method, the only method supported by the algorithm.

a

0

The mean a.

sigma

0.01

The standard deviation σ.

For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)