tf.compat.v1.layers.BatchNormalization

Batch Normalization layer from (Ioffe et al., 2015).

Inherits From: BatchNormalization, Layer, Layer, Module

Migrate to TF2

This API is not compatible with eager execution or tf.function.

Please refer to tf.layers section of the migration guide to migrate a TensorFlow v1 model to Keras. The corresponding TensorFlow v2 layer is tf.keras.layers.BatchNormalization.

Structural Mapping to Native TF2

None of the supported arguments have changed name.

Before:

 bn = tf.compat.v1.layers.BatchNormalization()

After:

 bn = tf.keras.layers.BatchNormalization()

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

Keras APIs handle BatchNormalization updates to the moving_mean and moving_variance as part of their fit() and evaluate() loops. However, if a custom training loop is used with an instance of Model, these updates need to be explicitly included. Here's a simple example of how it can be done:

  # model is an instance of Model that contains BatchNormalization layer.
  update_ops = model.get_updates_for(None) + model.get_updates_for(features)
  train_op = optimizer.minimize(loss)
  train_op = tf.group([train_op, update_ops])

axis An int or list of int, the axis or axes that should be normalized, typically the features axis/axes. For instance, after a Conv2D layer with data_format="channels_first", set axis=1. If a list of axes is provided, each axis in axis will be normalized simultaneously. Default is -1 which uses the last axis. Note: when using multi-axis batch norm, the beta, gamma, moving_mean, and moving_variance variables are the same rank as the input Tensor, with dimension size 1 in all reduced (non-axis) dimensions).
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.
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.
trainable Boolean, if True also add variables to the graph collection GraphKeys.TRAINABLE_VARIABLES (see tf.Variable).
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.
name A string, the name of the layer.

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)

graph

scope_name