Categorical crossentropy with integer targets.
k_sparse_categorical_crossentropy( target, output, from_logits = FALSE, axis = -1 )
An integer tensor.
A tensor resulting from a softmax (unless
from_logits is TRUE, in which case
output is expected to be the logits).
output is the result of a softmax, or is a tensor of logits.
Axis (axis indexes are 1-based). Pass -1 (the default) to select the last axis.
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: https://keras.rstudio.com/articles/backend.html#backend-functions.