This function takes a vector or 1 column matrix of class labels and converts it into a matrix with p columns, one for each category. This is the format most commonly used in the fitting and predicting of neural networks.
to_categorical(y, num_classes = NULL)
class vector to be converted into a matrix (integers from 0 to num_classes).
total number of classes. Set to NULL
to
autodetect from the input.
Taylor B. Arnold, taylor.arnold@acm.org
Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.