Initializers provide init values for network parameter blobs. In Caffe, they are called Fillers.

class NullInitializer

An initializer that does nothing. To initialize with zeros, use a ConstantInitializer.

class ConstantInitializer

Set everything to a constant.


The value used to initialize a parameter blob. Typically this is set to 0.

class XavierInitializer

An initializer based on [BengioGlorot2010], but does not use the fan-out value. It fills the parameter blob by randomly sampling uniform data from \([-S,S]\) where the scale \(S=\sqrt{3 / F_{\text{in}}}\). Here \(F_{\text{in}}\) is the fan-in: the number of input nodes.

Heuristics are used to determine the fan-in: For a ND tensor parameter blob, the product of all the 1 to N-1 dimensions are considered as fan-in, while the last dimension is considered as fan-out.

[BengioGlorot2010]Y. Bengio and X. Glorot, Understanding the difficulty of training deep feedforward neural networks, in Proceedings of AISTATS 2010, pp. 249-256.
class GaussianInitializer

Initialize each element in the parameter blob as independent and identically distributed Gaussian random variables.


Default 0.


Default 1.