Module init

Initialization

This module implements several initialization primitives for generating tensors using various distributions and strategies. The module is designed to be used in conjuction with the rand and rand_distr libraries. While ndarray_rand provides a RandomExt trait, we provide an alternative Initialize trait which is designed to be more flexible and better suited for machine-learning workloads.

Re-exports

pub use ndarray_rand as ndrand;

pub use rand;

pub use rand_distr;

pub use super::lecun::*;

pub use super::trunc::*;

pub use super::xavier::*;

Modules

distr

initializer

Traits

Initialize

This trait provides the base methods required for initializing an ndarray with random values. Initialize is similar to RandomExt, however, it focuses on flexibility while implementing additional features geared towards machine-learning models; such as lecun_normal initialization.

InitializeExt

This trait extends the Initialize trait with methods for generating random arrays from various distributions.

Functions

randc

Generate a random array of complex numbers with real and imaginary parts in the range [0, 1)

stdnorm

Given a shape, generate a random array using the StandardNormal distribution

stdnorm_from_seed

uniform_from_seed

Creates a random array from a uniform distribution using a given key