Package ai.djl.training.initializer

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.

Related Packages

Package	Description
ai.djl.training	Contains classes and implementations to train a neural network.

Class	Description
ConstantInitializer	Initializer that generates tensors with constant values.
Initializer	An interface representing an initialization method.
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.
XavierInitializer.FactorType	Enum for different types of factor type.
XavierInitializer.RandomType	Enum for different types of random distributions.