As shown below:
to_categorical(y, num_classes=None, dtype='float32')
Converts integer labels to onehot. y is an array of int's, num_classes is the total number of label categories, greater than max(y) (labels starting at 0).
Return: if num_classes=None, return len(y) * [max(y)+1] (dimension, m*n means m rows and n columns matrix, the same below), otherwise len(y) * num_classes. it seems complicated to say it out loud, please see the following example.
import keras ohl=.to_categorical([1,3]) # ohl=.to_categorical([[1],[3]]) print(ohl) """ [[0. 1. 0. 0.] [0. 0. 0. 1.]] """ ohl=.to_categorical([1,3],num_classes=5) print(ohl) """ [[0. 1. 0. 0. 0.] [0. 0. 0. 1. 0.]] """
The keras source code for this section is below:
def to_categorical(y, num_classes=None, dtype='float32'):
"""Converts a class vector (integers) to binary class matrix.
. for use with categorical_crossentropy.
# Arguments
y: class vector to be converted into a matrix
(integers from 0 to num_classes).
num_classes: total number of classes.
dtype: The data type expected by the input, as a string
(`float32`, `float64`, `int32`...)
# Returns
A binary matrix representation of the input. The classes axis
is placed last.
"""
y = (y, dtype='int')
input_shape =
if input_shape and input_shape[-1] == 1 and len(input_shape) > 1:
input_shape = tuple(input_shape[:-1])
y = ()
if not num_classes:
num_classes = (y) + 1
n = [0]
categorical = ((n, num_classes), dtype=dtype)
categorical[(n), y] = 1
output_shape = input_shape + (num_classes,)
categorical = (categorical, output_shape)
return categorical
Additional knowledge:keras notes - .to_categoracal() function
.to_categoracal (y, num_classes=None, dtype='float32')
Convert shaped labels to onehot, y is an int array, num_classes is the total number of label categories, greater than max (y), (labels starting from 0).
Return:
If num_classes=None, return len(y)*[max(y)+1] (dimension, m*n means m rows and n columns matrix), otherwise len(y)*num_classes.
The above this talk about .to_categorical usage in keras is all I have to share with you, I hope it can give you a reference, and I hope you will support me more.