chainer.functions.fixed_decorrelated_batch_normalization¶
-
chainer.functions.
fixed_decorrelated_batch_normalization
(x, mean, projection, groups=16)[source]¶ Decorrelated batch normalization function with fixed statistics.
This is a variant of decorrelated batch normalization, where the mean and projection statistics are given by the caller as fixed variables. This is used in testing mode of the decorrelated batch normalization layer, where batch statistics cannot be used for prediction consistency.
- Parameters
x (
Variable
) – Input variable.mean (
Variable
or N-dimensional array) – Shifting parameter of input.projection (
Variable
or N-dimensional array) – Projection matrix for decorrelation of input.groups (int) – Number of groups to use for group whitening.
- Returns
The output variable which has the same shape as \(x\).
- Return type