k_in_top_k

A tensor of shape <code>(batch_size, classes)</code> and type
<code>float32</code>.

predictions

A 1D tensor of length <code>batch_size</code> and type <code>int32</code> or
<code>int64</code>.

targets

An <code>int</code>, number of top elements to consider.

Returns whether the <code>targets</code> are in the top <code>k</code> <code>predictions</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.

Tomasz Kalinowski

keras

R Interface to 'Keras'

Daniel Falbel

JJ Allaire

Fran<c3><a7>ois Chollet

 RStudio

 Google

Yuan Tang

Wouter Van Der Bijl

Martin Studer

Sigrid Keydana

k_in_top_k 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>.

k_in_top_k: Returns whether the `targets` are in the top `k` `predictions`.

Description

Usage

Arguments

Value

Keras Backend