initializer_blockwise

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.

Tomasz Kalinowski

tfprobability

Interface to 'TensorFlow Probability'

Sigrid Keydana

Daniel Falbel

Kevin Kuo

RStudio 

initializer_blockwise function

<dl><dt>initializers</dt>
<dd>list of Keras initializers, eg: <code>keras::initializer_glorot_uniform()</code>
or <code>initializer_constant()</code>.</dd>
<dt>sizes</dt>
<dd>list of integers scalars representing the number of elements associated
with each initializer in <code>initializers</code>.</dd>
<dt>validate_args</dt>
<dd>bool indicating we should do (possibly expensive) graph-time
assertions, if necessary.
@return Initializer which concats other intializers</dd></dl>

Arguments

Blockwise Initializer — initializer_blockwise

<dl>

<dt>initializers</dt>
<dd>list of Keras initializers, eg: <code>keras::initializer_glorot_uniform()</code>
or <code>initializer_constant()</code>.</dd>


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


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

</dl>

initializer_blockwise: Blockwise Initializer

Description

Usage

Arguments