keras to_categorical 增加了额外的价值

Question

我有 4 个需要预测的类，我使用 kerasto_categorical来实现这一点，我希望得到一个 4one-hot-encoded数组，但似乎我得到了 5 个值，[0]所有行都会出现一个附加值

dict = {'word': 1, 'feature_name': 2, 'feature_value': 3, 'part_number': 4}
    Y = dataset['class'].apply(lambda label: dict[label])
    print(Y.unique()) #prints [1 4 2 3]
    train_x, test_x, train_y, test_y = model_selection.train_test_split(X, Y, test_size=0.2, random_state=0)
    train_y = to_categorical(train_y)
    print(train_y[0])# prints [0. 0. 1. 0. 0.]

我试图建立的模型如下

model = Sequential()
model.add(Dense(10, input_dim=input_dim, activation='relu'))
model.add(Dense(10, activation='relu'))
model.add(Dense(10, activation='relu'))
model.add(Dense(10, activation='relu'))
model.add(Dense(4, activation='softmax'))

但后来它一直在扔

ValueError: Error when checking target: expected dense_5 to have shape (4,) but got array with shape (5,)

Answer 1

您需要对从 0 开始的类进行编号，如下所示：

dict = {'word': 0, 'feature_name': 1, 'feature_value': 2, 'part_number': 3}

您可以使用 help() 命令获取该函数的描述

help(np_utils.to_categorical)

:

Help on function to_categorical in module keras.utils.np_utils:

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.

Answer 2

可能是keras版本错误。尝试更新它，因为这对我有用：

dict = {'word': 1, 'feature_name': 2, 'feature_value': 3, 'part_number': 4}
Y = np.random.randint(4, size=10)
print(np.unique(Y)) #prints [0 1 2 3]
train_y = np_utils.to_categorical(Y, num_classes=4)
print(train_y[0]) # prints [0. 0. 1. 0.]

尝试从 0 开始字典，因为当 Keras 读取数据时以 0 作为参考。

dict = {'word': 0, 'feature_name': 1, 'feature_value': 2, 'part_number': 3}

如果不起作用，尝试强制类数：

train_y = to_categorical(train_y, num_classes = 4)