tf.contrib.distributions.matrix_diag_transform(
matrix,
transform=None,
name=None
)
Defined in tensorflow/python/ops/distributions/util.py
.
Transform diagonal of [batch-]matrix, leave rest of matrix unchanged.
Create a trainable covariance defined by a Cholesky factor:
# Transform network layer into 2 x 2 array.
matrix_values = tf.contrib.layers.fully_connected(activations, 4)
matrix = tf.reshape(matrix_values, (batch_size, 2, 2))
# Make the diagonal positive. If the upper triangle was zero, this would be a
# valid Cholesky factor.
chol = matrix_diag_transform(matrix, transform=tf.nn.softplus)
# LinearOperatorLowerTriangular ignores the upper triangle.
operator = LinearOperatorLowerTriangular(chol)
Example of heteroskedastic 2-D linear regression.
tfd = tfp.distributions
# Get a trainable Cholesky factor.
matrix_values = tf.contrib.layers.fully_connected(activations, 4)
matrix = tf.reshape(matrix_values, (batch_size, 2, 2))
chol = matrix_diag_transform(matrix, transform=tf.nn.softplus)
# Get a trainable mean.
mu = tf.contrib.layers.fully_connected(activations, 2)
# This is a fully trainable multivariate normal!
dist = tfd.MultivariateNormalTriL(mu, chol)
# Standard log loss. Minimizing this will "train" mu and chol, and then dist
# will be a distribution predicting labels as multivariate Gaussians.
loss = -1 * tf.reduce_mean(dist.log_prob(labels))
Args:
matrix
: RankR
Tensor
,R >= 2
, where the last two dimensions are equal.transform
: Element-wise function mappingTensors
toTensors
. To be applied to the diagonal ofmatrix
. IfNone
,matrix
is returned unchanged. Defaults toNone
.name
: A name to give created ops. Defaults to "matrix_diag_transform".
Returns:
A Tensor
with same shape and dtype
as matrix
.