Module: tf.initializers

Public API for tf.initializers namespace.

Classes

class constant: Initializer that generates tensors with constant values.

class glorot_normal: The Glorot normal initializer, also called Xavier normal initializer.

class glorot_uniform: The Glorot uniform initializer, also called Xavier uniform initializer.

class identity: Initializer that generates the identity matrix.

class ones: Initializer that generates tensors initialized to 1.

class orthogonal: Initializer that generates an orthogonal matrix.

class random_normal: Initializer that generates tensors with a normal distribution.

class random_uniform: Initializer that generates tensors with a uniform distribution.

class truncated_normal: Initializer that generates a truncated normal distribution.

class uniform_unit_scaling: Initializer that generates tensors without scaling variance.

class variance_scaling: Initializer capable of adapting its scale to the shape of weights tensors.

class zeros: Initializer that generates tensors initialized to 0.

Functions

global_variables(...): Returns an Op that initializes global variables.

he_normal(...): He normal initializer.

he_uniform(...): He uniform variance scaling initializer.

lecun_normal(...): LeCun normal initializer.

lecun_uniform(...): LeCun uniform initializer.

local_variables(...): Returns an Op that initializes all local variables.

tables_initializer(...): Returns an Op that initializes all tables of the default graph.

variables(...): Returns an Op that initializes a list of variables.