Table Of Contents
Table Of Contents


Weight initializer.

Initialization methods

Bilinear() Initialize weight for upsampling layers.
Constant(value) Initializes the weights to a given value.
FusedRNN(init, num_hidden, num_layers, mode) Initialize parameters for fused rnn layers.
InitDesc Descriptor for the initialization pattern.
Initializer(**kwargs) The base class of an initializer.
LSTMBias([forget_bias]) Initialize all biases of an LSTMCell to 0.0 except for the forget gate whose bias is set to custom value.
Load(param[, default_init, verbose]) Initializes variables by loading data from file or dict.
MSRAPrelu([factor_type, slope]) Initialize the weight according to a MSRA paper.
Mixed(patterns, initializers) Initialize parameters using multiple initializers.
Normal([sigma]) Initializes weights with random values sampled from a normal distribution with a mean of zero and standard deviation of sigma.
One() Initializes weights to one.
Orthogonal([scale, rand_type]) Initialize weight as orthogonal matrix.
Uniform([scale]) Initializes weights with random values uniformly sampled from a given range.
Xavier([rnd_type, factor_type, magnitude]) Returns an initializer performing “Xavier” initialization for weights.
Zero() Initializes weights to zero.

Helper functions

register(klass) Registers a custom initializer.