Package org.tensorflow.framework.initializers

package org.tensorflow.framework.initializers

Class	Description
BaseInitializer<T extends TType>	Abstract base class for all Initializers
Constant<T extends TType>	Initializer that generates tensors with a constant value.
Glorot<T extends TFloating>	The Glorot initializer, also called Xavier initializer.
He<T extends TFloating>	He initializer.
Identity<T extends TFloating>	Initializer that generates the identity matrix.
Initializer<T extends TType>	An interface for Initializers
LeCun<T extends TFloating>	LeCun normal initializer.
Ones<T extends TType>	Initializer that generates tensors initialized to 1.
Orthogonal<T extends TFloating>	Initializer that generates an orthogonal matrix.
RandomNormal<T extends TFloating>	Initializer that generates tensors with a normal distribution.
RandomUniform<T extends TNumber>	Initializer that generates tensors with a uniform distribution.
TruncatedNormal<T extends TFloating>	Initializer that generates a truncated normal distribution.
VarianceScaling<T extends TFloating>	Initializer capable of adapting its scale to the shape of weights tensors.
VarianceScaling.Distribution	The random distribution to use when initializing the values.
VarianceScaling.Mode	The mode to use for calculating the fan values.
Zeros<T extends TType>	Creates an Initializer that sets all values to zero.