--- a
+++ b/man/evaluate_softmax.Rd
@@ -0,0 +1,33 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/evaluation.R
+\name{evaluate_softmax}
+\alias{evaluate_softmax}
+\title{Evaluate matrices of true targets and predictions from layer with softmax activation.}
+\usage{
+evaluate_softmax(y, y_conf, auc = FALSE, auprc = FALSE, label_names = NULL)
+}
+\arguments{
+\item{y}{Matrix of true target.}
+
+\item{y_conf}{Matrix of predictions.}
+
+\item{auc}{Whether to include AUC metric. Only possible for 2 targets.}
+
+\item{auprc}{Whether to include AUPRC metric. Only possible for 2 targets.}
+
+\item{label_names}{Names of corresponding labels. Length must be equal to number of columns of \code{y}.}
+}
+\value{
+A list of evaluation results.
+}
+\description{
+Compute confusion matrix, accuracy, categorical crossentropy and (optionally) AUC or AUPRC, given predictions and
+true targets. AUC and AUPRC only possible for 2 targets.
+}
+\examples{
+\dontshow{if (reticulate::py_module_available("tensorflow")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
+y <- matrix(c(1, 0, 0, 0, 1, 1), ncol = 2)
+y_conf <- matrix(c(0.3, 0.5, 0.1, 0.7, 0.5, 0.9), ncol = 2)
+evaluate_softmax(y, y_conf, auc = TRUE, auprc = TRUE, label_names = c("A", "B")) 
+\dontshow{\}) # examplesIf}
+}