to_categorical(y, num_classes=None, dtype='float32')

將整型標籤轉為onehot。y為int陣列，num_classes為標籤類別總數，大於max(y)（標籤從0開始的）。

返回：如果num_classes=None，返回len(y) * [max(y)+1]（維度，m*n表示m行n列矩陣，下同），否則為len(y) * num_classes。

import keras

ohl=keras.utils.to_categorical([1,3])
# ohl=keras.utils.to_categorical([[1],[3]])
print
 
(ohl)
"""
[[0. 1. 0. 0.]
 [0. 0. 0. 1.]]
"""
ohl=keras.utils.to_categorical([1,3],num_classes=5)
print(ohl)
"""
[[0. 1. 0. 0. 0.]
 [0. 0. 0. 1. 0.]]
"""

該部分keras原始碼如下：

def to_categorical(y, num_classes=None, dtype='float32'):
    """Converts a class vector (integers) to binary class matrix.

    E.g. 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 = np.array(y, dtype='int')
    input_shape = y.shape
    if input_shape and input_shape[-1] == 1 and len(input_shape) > 1:
        input_shape = tuple(input_shape[:-1])
    y = y.ravel()
    if not num_classes:
        num_classes = np.max(y) + 1
    n = y.shape[0]
    categorical = np.zeros(
 
(n, num_classes), dtype=dtype)
    categorical[np.arange(n), y] = 1
    output_shape = input_shape + (num_classes,)
    categorical = np.reshape(categorical, output_shape)
    return categorical