tfp.experimental.substrates.numpy.util.DeferredTensor

Variable tracking object which applies function upon convert_to_tensor.

Example

from tensorflow_probability.python.internal.backend.numpy.compat import v2 as tf
import tensorflow_probability as tfp; tfp = tfp.experimental.substrates.numpy
tfb = tfp.bijectors
tfd = tfp.distributions

# Note: it'd be better to use `tfp.util.TransformedVariable`;
#       this example is for illustration only.
trainable_normal = tfd.Normal(
    loc=tf.Variable(0.),
    scale=tfp.util.DeferredTensor(tf.Variable(0.), tf.math.exp))

trainable_normal.loc
# ==> <tf.Variable 'Variable:0' shape=() dtype=float32, numpy=0.0>

trainable_normal.scale
# ==> <DeferredTensor: dtype=float32, shape=[], fn=exp>

# Operators work with `DeferredTensor`.
trainable_normal.scale + 1.
# ==> 2.

with tf.GradientTape() as tape:
  negloglik = -trainable_normal.log_prob(0.5)
g = tape.gradient(negloglik, trainable_normal.trainable_variables)
# ==> (-0.5, 0.75)

Which we could then fit as:

opt = tf.optimizers.Adam(learning_rate=0.05)
loss = tf.function(lambda: -trainable_normal.log_prob(0.5), autograph=True)
for _ in range(int(1e3)):
  opt.minimize(loss, trainable_normal.trainable_variables)
trainable_normal.mean()
# ==> 0.5
trainable_normal.stddev()
# ==> (approximately) 0.0075

It is also possible to parameterize a DeferredTensor with a bijector, e.g.:

# Note: it'd be better to use `tfp.util.TransformedVariable`;
#       this example is for illustration only.
d = tfd.Normal(loc=0.,
               scale=tfp.util.DeferredTensor(tf.Variable([0.54, 1.85]),
                                             tfb.Softplus()))
d.stddev()
# ==> [1., 2.]
tf.convert_to_tensor(d.scale)
# ==> [1., 2.]

pretransformed_input object with shape, dtype properties (typically a tf.Variable) passed into transform_fn when this object is acted upon in a Tensor context, eg, tf.convert_to_tensor, +, tf.math.exp, etc.
transform_fn Python callable or tfp.bijectors.Bijector-like instance. When callable, should take pretransformed_input and return a Tensor (representing by this object).
dtype Equivalent to what would otherwise be transform_fn(pretransformed_input).dtype. Default value: None (i.e., getattr(transform_fn, 'dtype', None) or pretransformed_input.dtype).
shape Equivalent to what would otherwise be transform_fn(pretransformed_input).shape. Default value: 'None' (i.e., getattr(transform_fn, 'forward_event_shape', lambda x: x)( pretransformed_input.shape)).
name Python str representing this object's name; used only in graph mode. Default value: None (i.e., (getattr(transform_fn, 'name', None) or transform_fn.__name__ + '_' + pretransformed_input.name)).

TypeError if transform_fn is not callable.
TypeError if pretransformed_input lacks dtype and/or shape properties (and dtype and/or shape arguments are unspecified).

dtype Represents the type of the elements in a Tensor.
name The string name of this object.
pretransformed_input Input to transform_fn.
shape Represents the shape of a Tensor.
trainable_variables

transform_fn Function which characterizes the Tensorization of this object.
variables

Methods

get_shape

View source

Legacy means of getting Tensor shape, for compat with 2.0.0 LinOp.

numpy

View source

Returns (copy of) deferred values as a NumPy array or scalar.

set_shape

View source

Updates the shape of this pretransformed_input.

This method can be called multiple times, and will merge the given shape with the current shape of this object. It can be used to provide additional information about the shape of this object that cannot be inferred from the graph alone.

Args
shape A TensorShape representing the shape of this pretransformed_input, a TensorShapeProto, a list, a tuple, or None.

Raises
ValueError If shape is not compatible with the current shape of this pretransformed_input.

__getitem__

View source