initializer_blockwise

list of Keras initializers, eg: <code><a rd-options="keras:initializer_glorot_uniform" href="/link/keras%3A%3Ainitializer_glorot_uniform()?package=tfprobability&version=0.12.0.0&to=keras%3Ainitializer_glorot_uniform" data-mini-rdoc="keras:initializer_glorot_uniform::keras::initializer_glorot_uniform()">keras::initializer_glorot_uniform()</a></code>
or <code><a rd-options="=initializer_constant" href="/link/initializer_constant()?package=tfprobability&version=0.12.0.0&to=%3Dinitializer_constant" data-mini-rdoc="=initializer_constant::initializer_constant()">initializer_constant()</a></code>.

initializers

list of integers scalars representing the number of elements associated
with each initializer in <code>initializers</code>.

sizes

bool indicating we should do (possibly expensive) graph-time
assertions, if necessary.
@return Initializer which concats other intializers

validate_args

Initializer which concats other intializers

Interface to 'TensorFlow Probability', a 'Python' library built on 'TensorFlow'
that makes it easy to combine probabilistic models and deep learning on modern hardware ('TPU', 'GPU').
'TensorFlow Probability' includes a wide selection of probability distributions and bijectors, probabilistic layers,
variational inference, Markov chain Monte Carlo, and optimizers such as Nelder-Mead, BFGS, and SGLD.

Sigrid Keydana

tfprobability

Interface to 'TensorFlow Probability'

Daniel Falbel

Kevin Kuo

 RStudio

initializer_blockwise function

list of Keras initializers, eg: <code><a rd-options='keras:initializer_glorot_uniform' href='keras::initializer_glorot_uniform()'>keras::initializer_glorot_uniform()</a></code>
or <code><a rd-options='=initializer_constant' href='initializer_constant()'>initializer_constant()</a></code>.

initializer_blockwise: Blockwise Initializer

Description

Usage

Arguments