Skip to contents

Batch normalization applies a transformation that maintains the mean output close to 0 and the output standard deviation close to 1.

Importantly, batch normalization works differently during training and during inference.

During training (i.e. when using fit() or when calling the layer/model with the argument training = TRUE), the layer normalizes its output using the mean and standard deviation of the current batch of inputs. That is to say, for each channel being normalized, the layer returns gamma * (batch - mean(batch)) / sqrt(var(batch) + epsilon) + beta, where:

  • epsilon is small constant (configurable as part of the constructor arguments)

  • gamma is a learned scaling factor (initialized as 1), which can be disabled by passing scale = FALSE to the constructor.

  • beta is a learned offset factor (initialized as 0), which can be disabled by passing center = FALSE to the constructor.

During inference (i.e. when using evaluate() or predict() or when calling the layer/model with the argument training = FALSE (which is the default), the layer normalizes its output using a moving average of the mean and standard deviation of the batches it has seen during training. That is to say, it returns gamma * (batch - self$moving_mean) / sqrt(self$moving_var+epsilon) + beta.

self$moving_mean and self$moving_var are non-trainable variables that are updated each time the layer in called in training mode, as such:

  • moving_mean = moving_mean * momentum + mean(batch) * (1 - momentum)

  • moving_var = moving_var * momentum + var(batch) * (1 - momentum)

As such, the layer will only normalize its inputs during inference after having been trained on data that has similar statistics as the inference data.

About setting layer$trainable <- FALSE on a BatchNormalization layer:

The meaning of setting layer$trainable <- FALSE is to freeze the layer, i.e. its internal state will not change during training: its trainable weights will not be updated during fit() or train_on_batch(), and its state updates will not be run.

Usually, this does not necessarily mean that the layer is run in inference mode (which is normally controlled by the training argument that can be passed when calling a layer). "Frozen state" and "inference mode" are two separate concepts.

However, in the case of the BatchNormalization layer, setting trainable <- FALSE on the layer means that the layer will be subsequently run in inference mode (meaning that it will use the moving mean and the moving variance to normalize the current batch, rather than using the mean and variance of the current batch).

Note that:

  • Setting trainable on an model containing other layers will recursively set the trainable value of all inner layers.

  • If the value of the trainable attribute is changed after calling compile() on a model, the new value doesn't take effect for this model until compile() is called again.

Usage

layer_batch_normalization(
  object,
  axis = -1L,
  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,
  synchronized = FALSE,
  ...
)

Arguments

object

Object to compose the layer with. A tensor, array, or sequential model.

axis

Integer, the axis that should be normalized (typically the features axis). For instance, after a Conv2D layer with data_format = "channels_first", use axis = 2.

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 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.

synchronized

Only applicable with the TensorFlow backend. If TRUE, synchronizes the global batch statistics (mean and variance) for the layer across all devices at each training step in a distributed training strategy. If FALSE, each replica uses its own local batch statistics.

...

Base layer keyword arguments (e.g. name and dtype).

Value

The return value depends on the value provided for the first argument. If object is:

  • a keras_model_sequential(), then the layer is added to the sequential model (which is modified in place). To enable piping, the sequential model is also returned, invisibly.

  • a keras_input(), then the output tensor from calling layer(input) is returned.

  • NULL or missing, then a Layer instance is returned.

Call Arguments

  • inputs: Input tensor (of any rank).

  • training: R boolean indicating whether the layer should behave in training mode or in inference mode.

    • training = TRUE: The layer will normalize its inputs using the mean and variance of the current batch of inputs.

    • training = FALSE: The layer will normalize its inputs using the mean and variance of its moving statistics, learned during training.

  • mask: Binary tensor of shape broadcastable to inputs tensor, with TRUE values indicating the positions for which mean and variance should be computed. Masked elements of the current inputs are not taken into account for mean and variance computation during training. Any prior unmasked element values will be taken into account until their momentum expires.

See also

Other normalization layers:
layer_group_normalization()
layer_layer_normalization()
layer_spectral_normalization()
layer_unit_normalization()

Other layers:
Layer()
layer_activation()
layer_activation_elu()
layer_activation_leaky_relu()
layer_activation_parametric_relu()
layer_activation_relu()
layer_activation_softmax()
layer_activity_regularization()
layer_add()
layer_additive_attention()
layer_alpha_dropout()
layer_attention()
layer_average()
layer_average_pooling_1d()
layer_average_pooling_2d()
layer_average_pooling_3d()
layer_bidirectional()
layer_category_encoding()
layer_center_crop()
layer_concatenate()
layer_conv_1d()
layer_conv_1d_transpose()
layer_conv_2d()
layer_conv_2d_transpose()
layer_conv_3d()
layer_conv_3d_transpose()
layer_conv_lstm_1d()
layer_conv_lstm_2d()
layer_conv_lstm_3d()
layer_cropping_1d()
layer_cropping_2d()
layer_cropping_3d()
layer_dense()
layer_depthwise_conv_1d()
layer_depthwise_conv_2d()
layer_discretization()
layer_dot()
layer_dropout()
layer_einsum_dense()
layer_embedding()
layer_feature_space()
layer_flatten()
layer_gaussian_dropout()
layer_gaussian_noise()
layer_global_average_pooling_1d()
layer_global_average_pooling_2d()
layer_global_average_pooling_3d()
layer_global_max_pooling_1d()
layer_global_max_pooling_2d()
layer_global_max_pooling_3d()
layer_group_normalization()
layer_group_query_attention()
layer_gru()
layer_hashed_crossing()
layer_hashing()
layer_identity()
layer_integer_lookup()
layer_lambda()
layer_layer_normalization()
layer_lstm()
layer_masking()
layer_max_pooling_1d()
layer_max_pooling_2d()
layer_max_pooling_3d()
layer_maximum()
layer_minimum()
layer_multi_head_attention()
layer_multiply()
layer_normalization()
layer_permute()
layer_random_brightness()
layer_random_contrast()
layer_random_crop()
layer_random_flip()
layer_random_rotation()
layer_random_translation()
layer_random_zoom()
layer_repeat_vector()
layer_rescaling()
layer_reshape()
layer_resizing()
layer_rnn()
layer_separable_conv_1d()
layer_separable_conv_2d()
layer_simple_rnn()
layer_spatial_dropout_1d()
layer_spatial_dropout_2d()
layer_spatial_dropout_3d()
layer_spectral_normalization()
layer_string_lookup()
layer_subtract()
layer_text_vectorization()
layer_tfsm()
layer_time_distributed()
layer_torch_module_wrapper()
layer_unit_normalization()
layer_upsampling_1d()
layer_upsampling_2d()
layer_upsampling_3d()
layer_zero_padding_1d()
layer_zero_padding_2d()
layer_zero_padding_3d()
rnn_cell_gru()
rnn_cell_lstm()
rnn_cell_simple()
rnn_cells_stack()