tf.contrib.distributions.bijectors.BatchNormalization

Class BatchNormalization

Inherits From: Bijector

Defined in tensorflow/contrib/distributions/python/ops/bijectors/batch_normalization.py.

Compute Y = g(X) s.t. X = g^-1(Y) = (Y - mean(Y)) / std(Y).

Applies Batch Normalization [(Ioffe and Szegedy, 2015)][1] to samples from a data distribution. This can be used to stabilize training of normalizing flows ([Papamakarios et al., 2016][3]; [Dinh et al., 2017][2])

When training Deep Neural Networks (DNNs), it is common practice to normalize or whiten features by shifting them to have zero mean and scaling them to have unit variance.

The inverse() method of the BatchNormalization bijector, which is used in the log-likelihood computation of data samples, implements the normalization procedure (shift-and-scale) using the mean and standard deviation of the current minibatch.

Conversely, the forward() method of the bijector de-normalizes samples (e.g. X*std(Y) + mean(Y) with the running-average mean and standard deviation computed at training-time. De-normalization is useful for sampling.

dist = tfd.TransformedDistribution(
    distribution=tfd.Normal()),
    bijector=tfb.BatchNorm())

y = tfd.MultivariateNormalDiag(loc=1., scale=2.).sample(100)  # ~ N(1, 2)
x = dist.bijector.inverse(y)  # ~ N(0, 1)
y = dist.sample()  # ~ N(1, 2)

During training time, BatchNorm.inverse and BatchNorm.forward are not guaranteed to be inverses of each other because inverse(y) uses statistics of the current minibatch, while forward(x) uses running-average statistics accumulated from training. In other words, BatchNorm.inverse(BatchNorm.forward(...)) and BatchNorm.forward(BatchNorm.inverse(...)) will be identical when training=False but may be different when training=True.

References

[1]: Sergey Ioffe and Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning, 2015. https://arxiv.org/abs/1502.03167

[2]: Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. Density Estimation using Real NVP. In International Conference on Learning Representations, 2017. https://arxiv.org/abs/1605.08803

[3]: George Papamakarios, Theo Pavlakou, and Iain Murray. Masked Autoregressive Flow for Density Estimation. In Neural Information Processing Systems, 2017. https://arxiv.org/abs/1705.07057

Properties

dtype

dtype of Tensors transformable by this distribution.

event_ndims

Returns then number of event dimensions this bijector operates on.

graph_parents

Returns this Bijector's graph_parents as a Python list.

is_constant_jacobian

Returns true iff the Jacobian is not a function of x.

Note: Jacobian is either constant for both forward and inverse or neither.

Returns:

• is_constant_jacobian: Python bool.

name

Returns the string name of this Bijector.

validate_args

Returns True if Tensor arguments will be validated.

Methods

__init__

__init__(
    batchnorm_layer=None,
    training=True,
    validate_args=False,
    name='batch_normalization'
)

Instantiates the BatchNorm bijector.

Args:

• batchnorm_layer: tf.layers.BatchNormalization layer object. If None, defaults to tf.layers.BatchNormalization(gamma_constraint=nn_ops.relu(x) + 1e-6). This ensures positivity of the scale variable.

• training: If True, updates running-average statistics during call to inverse().

• validate_args: Python bool indicating whether arguments should be checked for correctness.
• name: Python str name given to ops managed by this object.

Raises:

• ValueError: If bn_layer is not an instance of tf.layers.BatchNormalization, or if it is specified with renorm=True or a virtual batch size.

forward

forward(
    x,
    name='forward'
)

Returns the forward Bijector evaluation, i.e., X = g(Y).

Args:

• x: Tensor. The input to the "forward" evaluation.
• name: The name to give this op.

Returns:

Tensor.

Raises:

• TypeError: if self.dtype is specified and x.dtype is not self.dtype.
• NotImplementedError: if _forward is not implemented.

forward_event_shape

forward_event_shape(input_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as forward_event_shape_tensor. May be only partially defined.

Args:

• input_shape: TensorShape indicating event-portion shape passed into forward function.

Returns:

• forward_event_shape_tensor: TensorShape indicating event-portion shape after applying forward. Possibly unknown.

forward_event_shape_tensor

forward_event_shape_tensor(
    input_shape,
    name='forward_event_shape_tensor'
)

Shape of a single sample from a single batch as an int32 1D Tensor.

Args:

• input_shape: Tensor, int32 vector indicating event-portion shape passed into forward function.
• name: name to give to the op

Returns:

• forward_event_shape_tensor: Tensor, int32 vector indicating event-portion shape after applying forward.

forward_log_det_jacobian

forward_log_det_jacobian(
    x,
    name='forward_log_det_jacobian'
)

Returns both the forward_log_det_jacobian.

Args:

• x: Tensor. The input to the "forward" Jacobian evaluation.
• name: The name to give this op.

Returns:

Tensor, if this bijector is injective. If not injective this is not implemented.

Raises:

• TypeError: if self.dtype is specified and y.dtype is not self.dtype.
• NotImplementedError: if neither _forward_log_det_jacobian nor {_inverse, _inverse_log_det_jacobian} are implemented, or this is a non-injective bijector.

inverse

inverse(
    y,
    name='inverse'
)

Returns the inverse Bijector evaluation, i.e., X = g^{-1}(Y).

Args:

• y: Tensor. The input to the "inverse" evaluation.
• name: The name to give this op.

Returns:

Tensor, if this bijector is injective. If not injective, returns the k-tuple containing the unique k points (x1, ..., xk) such that g(xi) = y.

Raises:

• TypeError: if self.dtype is specified and y.dtype is not self.dtype.
• NotImplementedError: if _inverse is not implemented.

inverse_event_shape

inverse_event_shape(output_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as inverse_event_shape_tensor. May be only partially defined.

Args:

• output_shape: TensorShape indicating event-portion shape passed into inverse function.

Returns:

• inverse_event_shape_tensor: TensorShape indicating event-portion shape after applying inverse. Possibly unknown.

inverse_event_shape_tensor

inverse_event_shape_tensor(
    output_shape,
    name='inverse_event_shape_tensor'
)

Shape of a single sample from a single batch as an int32 1D Tensor.

Args:

• output_shape: Tensor, int32 vector indicating event-portion shape passed into inverse function.
• name: name to give to the op

Returns:

• inverse_event_shape_tensor: Tensor, int32 vector indicating event-portion shape after applying inverse.

inverse_log_det_jacobian

inverse_log_det_jacobian(
    y,
    name='inverse_log_det_jacobian'
)

Returns the (log o det o Jacobian o inverse)(y).

Mathematically, returns: log(det(dX/dY))(Y). (Recall that: X=g^{-1}(Y).)

Note that forward_log_det_jacobian is the negative of this function, evaluated at g^{-1}(y).

Args:

• y: Tensor. The input to the "inverse" Jacobian evaluation.
• name: The name to give this op.

Returns:

Tensor, if this bijector is injective. If not injective, returns the tuple of local log det Jacobians, log(det(Dg_i^{-1}(y))), where g_i is the restriction of g to the ith partition Di.

Raises:

• TypeError: if self.dtype is specified and y.dtype is not self.dtype.
• NotImplementedError: if _inverse_log_det_jacobian is not implemented.