tf.compat.v1.layers.batch_normalization

Functional interface for the batch normalization layer from_config(Ioffe et al., 2015).

tf.compat.v1.layers.batch_normalization(
    inputs,
    axis=-1,
    momentum=0.99,
    epsilon=0.001,
    center=True,
    scale=True,
    beta_initializer=tf.compat.v1.zeros_initializer(),
    gamma_initializer=tf.compat.v1.ones_initializer(),
    moving_mean_initializer=tf.compat.v1.zeros_initializer(),
    moving_variance_initializer=tf.compat.v1.ones_initializer(),
    beta_regularizer=None,
    gamma_regularizer=None,
    beta_constraint=None,
    gamma_constraint=None,
    training=False,
    trainable=True,
    name=None,
    reuse=None,
    renorm=False,
    renorm_clipping=None,
    renorm_momentum=0.99,
    fused=None,
    virtual_batch_size=None,
    adjustment=None
)

Migrate to TF2

Caution: This API was designed for TensorFlow v1. Continue reading for details on how to migrate from this API to a native TensorFlow v2 equivalent. See the TensorFlow v1 to TensorFlow v2 migration guide for instructions on how to migrate the rest of your code.

This API is a legacy api that is only compatible with eager execution and tf.function if you combine it with tf.compat.v1.keras.utils.track_tf1_style_variables

Please refer to tf.layers model mapping section of the migration guide to learn how to use your TensorFlow v1 model in TF2 with Keras.

The corresponding TensorFlow v2 layer is tf.keras.layers.BatchNormalization.

The batch updating pattern with tf.control_dependencies(tf.GraphKeys.UPDATE_OPS) should not be used in native TF2. Consult the tf.keras.layers.BatchNormalization documentation for further information.

Structural Mapping to Native TF2

None of the supported arguments have changed name.

Before:

 x_norm = tf.compat.v1.layers.batch_normalization(x)

After:

To migrate code using TF1 functional layers use the Keras Functional API:

 x = tf.keras.Input(shape=(28, 28, 1),)
 y = tf.keras.layers.BatchNormalization()(x)
 model = tf.keras.Model(x, y)

How to Map Arguments

TF1 Arg Name	TF2 Arg Name	Note
name	name	Layer base class
trainable	trainable	Layer base class
axis	axis	-
momentum	momentum	-
epsilon	epsilon	-
center	center	-
scale	scale	-
beta_initializer	beta_initializer	-
gamma_initializer	gamma_initializer	-
moving_mean_initializer	moving_mean_initializer	-
beta_regularizer	`beta_regularizer'	-
gamma_regularizer	`gamma_regularizer'	-
beta_constraint	`beta_constraint'	-
gamma_constraint	`gamma_constraint'	-
renorm	Not supported	-
renorm_clipping	Not supported	-
renorm_momentum	Not supported	-
fused	Not supported	-
virtual_batch_size	Not supported	-
adjustment	Not supported	-

Description

Note: when training, the moving_mean and moving_variance need to be updated. By default the update ops are placed in tf.GraphKeys.UPDATE_OPS, so they need to be executed alongside the train_op. Also, be sure to add any batch_normalization ops before getting the update_ops collection. Otherwise, update_ops will be empty, and training/inference will not work properly. For example:

  x_norm = tf.compat.v1.layers.batch_normalization(x, training=training)

  # ...

  update_ops = tf.compat.v1.get_collection(tf.GraphKeys.UPDATE_OPS)
  train_op = optimizer.minimize(loss)
  train_op = tf.group([train_op, update_ops])

Args
inputs	Tensor input.
axis	An int, the axis that should be normalized (typically the features axis). For instance, after a Convolution2D layer with data_format="channels_first", set axis=1 in BatchNormalization.
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 can 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	An optional projection function to be applied to the beta weight after being updated by an Optimizer (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training.
gamma_constraint	An optional projection function to be applied to the gamma weight after being updated by an Optimizer.
training	Either a Python boolean, or a TensorFlow boolean scalar tensor (e.g. a placeholder). Whether to return the output in training mode (normalized with statistics of the current batch) or in inference mode (normalized with moving statistics). NOTE: make sure to set this parameter correctly, or else your training/inference will not work properly.
trainable	Boolean, if True also add variables to the graph collection GraphKeys.TRAINABLE_VARIABLES (see tf.Variable).
name	String, the name of the layer.
reuse	Boolean, whether to reuse the weights of a previous layer by the same name.
renorm	Whether to use Batch Renormalization (Ioffe, 2017). This adds extra variables during training. The inference is the same for either value of this parameter.
renorm_clipping	A dictionary that may map keys 'rmax', 'rmin', 'dmax' to scalar Tensors used to clip the renorm correction. The correction (r, d) is used as corrected_value = normalized_value * r + d, with r clipped to [rmin, rmax], and d to [-dmax, dmax]. Missing rmax, rmin, dmax are set to inf, 0, inf, respectively.
renorm_momentum	Momentum used to update the moving means and standard deviations with renorm. Unlike momentum, this affects training and should be neither too small (which would add noise) nor too large (which would give stale estimates). Note that momentum is still applied to get the means and variances for inference.
fused	if None or True, use a faster, fused implementation if possible. If False, use the system recommended implementation.
virtual_batch_size	An int. By default, virtual_batch_size is None, which means batch normalization is performed across the whole batch. When virtual_batch_size is not None, instead perform "Ghost Batch Normalization", which creates virtual sub-batches which are each normalized separately (with shared gamma, beta, and moving statistics). Must divide the actual batch size during execution.
adjustment	A function taking the Tensor containing the (dynamic) shape of the input tensor and returning a pair (scale, bias) to apply to the normalized values (before gamma and beta), only during training. For example, if axis==-1, adjustment = lambda shape: ( tf.random.uniform(shape[-1:], 0.93, 1.07), tf.random.uniform(shape[-1:], -0.1, 0.1)) will scale the normalized value by up to 7% up or down, then shift the result by up to 0.1 (with independent scaling and bias for each feature but shared across all examples), and finally apply gamma and/or beta. If None, no adjustment is applied. Cannot be specified if virtual_batch_size is specified.

Returns
Output tensor.

Raises
ValueError	if eager execution is enabled.

References
Batch Normalization - Accelerating Deep Network Training by Reducing Internal Covariate Shift: Ioffe et al., 2015 (pdf) Batch Renormalization - Towards Reducing Minibatch Dependence in Batch-Normalized Models: Ioffe, 2017 (pdf)