BatchNormalization.Builder |
BatchNormalization.Builder.beta(double beta) |
|
BatchNormalization.Builder |
BatchNormalization.Builder.constrainBeta(LayerConstraint... constraints) |
Set constraints to be applied to the beta parameter of this batch normalisation layer.
|
BatchNormalization.Builder |
BatchNormalization.Builder.constrainGamma(LayerConstraint... constraints) |
Set constraints to be applied to the gamma parameter of this batch normalisation layer.
|
BatchNormalization.Builder |
BatchNormalization.Builder.cudnnAllowFallback(boolean allowFallback) |
Deprecated.
|
BatchNormalization.Builder |
BatchNormalization.Builder.dataFormat(CNN2DFormat format) |
Set the input and output array data format.
|
BatchNormalization.Builder |
BatchNormalization.Builder.decay(double decay) |
At test time: we can use a global estimate of the mean and variance, calculated using a moving average of the
batch means/variances.
|
BatchNormalization.Builder |
BatchNormalization.Builder.eps(double eps) |
|
BatchNormalization.Builder |
BatchNormalization.Builder.gamma(double gamma) |
|
BatchNormalization.Builder |
BatchNormalization.Builder.helperAllowFallback(boolean allowFallback) |
When using CuDNN or MKLDNN and an error is encountered, should fallback to the non-helper implementation be allowed?
If set to false, an exception in the helper will be propagated back to the user.
|
BatchNormalization.Builder |
BatchNormalization.Builder.lockGammaBeta(boolean lockGammaBeta) |
If set to true: lock the gamma and beta parameters to the values for each activation, specified by gamma(double) and beta(double) .
|
BatchNormalization.Builder |
BatchNormalization.Builder.minibatch(boolean minibatch) |
If doing minibatch training or not.
|
BatchNormalization.Builder |
BatchNormalization.Builder.useLogStd(boolean useLogStd) |
How should the moving average of variance be stored? Two different parameterizations are supported.
|