mxnet.initializer¶
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. |