BatchNormalization: Batch normalization layer

In kerasR: R Interface to the Keras Deep Learning Library

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, [e-mail]

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.