tf.keras.layers.BatchNormalization

Layer that normalizes its inputs.

Inherits From: Layer, Operation

Used in the notebooks

Used in the guideUsed in the tutorials

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.

axisInteger, the axis that should be normalized (typically the features axis). For instance, after a Conv2D layer with data_format="channels_first", use axis=1.
momentumMomentum for the moving average.
epsilonSmall float added to variance to avoid dividing by zero.
centerIf True, add offset of beta to normalized tensor. If False, beta is ignored.
scaleIf 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_initializerInitializer for the beta weight.
gamma_initializerInitializer for the gamma weight.
moving_mean_initializerInitializer for the moving mean.
moving_variance_initializerInitializer for the moving variance.
beta_regularizerOptional regularizer for the beta weight.
gamma_regularizerOptional regularizer for the gamma weight.
beta_constraintOptional constraint for the beta weight.
gamma_constraintOptional constraint for the gamma weight.
synchronizedOnly 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.
**kwargsBase layer keyword arguments (e.g. name and dtype).

inputsInput tensor (of any rank).
trainingPython 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.
maskBinary 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.

Reference:

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.

inputRetrieves the input tensor(s) of a symbolic operation.

Only returns the tensor(s) corresponding to the first time the operation was called.

outputRetrieves the output tensor(s) of a layer.

Only returns the tensor(s) corresponding to the first time the operation was called.

Methods

from_config

View source

Creates a layer from its config.

This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).

Args
configA Python dictionary, typically the output of get_config.

Returns
A layer instance.

symbolic_call

View source