BatchNormalization: Batch normalization layer

View source: R/layers.normalization.R

BatchNormalizationR Documentation

Batch normalization layer

Description

Batch normalization layer

Usage

BatchNormalization(axis = -1, momentum = 0.99, epsilon = 0.001,
  center = TRUE, scale = TRUE, beta_initializer = "zeros",
  gamma_initializer = "ones", moving_mean_initializer = "zeros",
  moving_variance_initializer = "ones", beta_regularizer = NULL,
  gamma_regularizer = NULL, beta_constraint = NULL,
  gamma_constraint = NULL, input_shape = NULL)

Arguments

axis

Integer, the axis that should be normalized (typically the features axis).

momentum

Momentum for the moving average.

epsilon

Small float added to variance to avoid dividing by zero.

center

If True, add offset of beta to normalized tensor. If False, beta is ignored.

scale

If True, multiply by gamma. If False, gamma is not used. When the next layer is linear (also e.g. nn.relu), this can be disabled since the scaling will be done by the next layer.

beta_initializer

Initializer for the beta weight.

gamma_initializer

Initializer for the gamma weight.

moving_mean_initializer

Initializer for the moving mean.

moving_variance_initializer

Initializer for the moving variance.

beta_regularizer

Optional regularizer for the beta weight.

gamma_regularizer

Optional regularizer for the gamma weight.

beta_constraint

Optional constraint for the beta weight.

gamma_constraint

Optional constraint for the gamma weight.

input_shape

only need when first layer of a model; sets the input shape of the data

Author(s)

Taylor B. Arnold, taylor.arnold@acm.org

References

Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.

See Also

Other layers: Activation, ActivityRegularization, AdvancedActivation, Conv, Dense, Dropout, Embedding, Flatten, GaussianNoise, LayerWrapper, LocallyConnected, Masking, MaxPooling, Permute, RNN, RepeatVector, Reshape, Sequential

Examples

if(keras_available()) {
  X_train <- matrix(rnorm(100 * 10), nrow = 100)
  Y_train <- to_categorical(matrix(sample(0:2, 100, TRUE), ncol = 1), 3)
  
  mod <- Sequential()
  mod$add(Dense(units = 50, input_shape = dim(X_train)[2]))
  mod$add(Dropout(rate = 0.5))
  mod$add(Activation("relu"))
  mod$add(BatchNormalization())
  mod$add(Dense(units = 3))
  mod$add(ActivityRegularization(l1 = 1))
  mod$add(Activation("softmax"))
  keras_compile(mod,  loss = 'categorical_crossentropy', optimizer = RMSprop())
  
  keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5,
            verbose = 0, validation_split = 0.2)
}

kerasR documentation built on Aug. 17, 2022, 5:06 p.m.