k_gather

reference

Indices. Dimension indices are 1-based. Note however that if you pass a
tensor for <code>indices</code> they will be passed as-is, in which case indices will be 0 based
because no normalizing of R 1-based axes to Python 0-based axes is performed.

indices

Retrieves the elements of indices <code>indices</code> in the tensor <code>reference</code>.

Interface to 'Keras' <https://keras.io>, a high-level neural
networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation,
supports both convolution based networks and recurrent networks (as well as
combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Daniel Falbel

keras

R Interface to 'Keras'

JJ Allaire

Fran<c3><a7>ois Chollet

 RStudio

 Google

Yuan Tang

Wouter Van Der Bijl

Martin Studer

Sigrid Keydana

k_gather function

This function is part of a set of Keras backend functions that enable
lower level access to the core operations of the backend tensor engine
(e.g. TensorFlow, CNTK, Theano, etc.).
You can see a list of all available backend functions here:
<a href="https://keras.rstudio.com/articles/backend.html#backend-functions">https://keras.rstudio.com/articles/backend.html#backend-functions</a>.

Keras Backend

Retrieves the elements of indices <code>indices</code> in the tensor <code>reference</code>. — k_gather

Retrieves the elements of indices <code>indices</code> in the tensor <code>reference</code>.

k_gather: Retrieves the elements of indices `indices` in the tensor `reference`.

Description

Usage

Arguments

Value

Keras Backend