格式化标签为独热编码，keras.utils.np_utils.to_categorical

import numpy as np
from keras.utils.np_utils import to_categorical

a = np.array([1,0,0,1,0])

b = to_categorical(a)

print(a)
print('--------------')
print(b)

[1 0 0 1 0]
--------------
[[0. 1.]
 [1. 0.]
 [1. 0.]
 [0. 1.]
 [1. 0.]]