Package ai.djl.training.initializer

Contains classes for initializing a Block's Parameters.

It contains a main interface Initializer and various initializers that extend it.

Interface Summary

Interface	Description
Initializer	An interface representing an initialization method.

Class Summary

Class	Description
ConstantInitializer	Initializer that generates tensors with constant values.
NormalInitializer	NormalInitializer initializes weights with random values sampled from a normal distribution with a mean of zero and standard deviation of sigma.
TruncatedNormalInitializer	Naive implementation of a truncated normal initializer.
UniformInitializer	UniformInitializer initializes weights with random values uniformly sampled from a given range.
XavierInitializer	XavierInitializer is an Initializer that performs "Xavier" initialization for parameters.

Enum Summary

Enum	Description
XavierInitializer.FactorType	Enum for different types of factor type.
XavierInitializer.RandomType	Enum for different types of random distributions.