分类交叉熵和标签编码

Question

我正在尝试编写多类输出，类是 ['A','B','C','D','E','F','G']。

谁能详细说明下一个错误消息：

"ValueError: 您正在传递一个形状为 (79, 1) 的目标数组，而将其用作损失 categorical_crossentropy。categorical_crossentropy 期望目标是形状（样本、类）的二进制矩阵（1 和 0）。如果您的目标是整数类，您可以通过以下方式将它们转换为预期的格式： from keras.utils.np_utils import to_categorical y_binary = to_categorical(y_int)

或者，您可以改用损失函数sparse_categorical_crossentropy，它确实需要整数目标。”

我的代码：

# Part 1 - Data Preprocessing

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd 

# Importing the dataset
dataa = pd.read_csv('test_out.csv')

XX = dataa.iloc[:, 0:4].values
yy = dataa.iloc[:, 4].values

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_Y_1 = LabelEncoder()
yy = labelencoder_Y_1.fit_transform(yy)

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(XX, yy, test_size = 0.2, 
random_state = 0)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# Part 2 - Now let's make the ANN!

# Importing the Keras libraries and packages
import keras
from keras.models import Sequential
from keras.layers import Dense


# Initialising the ANN
classifier = Sequential()

# Adding the input layer and the first hidden layer
classifier.add(Dense(output_dim = 6, init = 'uniform', activation = 'relu', 
input_dim = 4))

# Adding the second hidden layer
classifier.add(Dense(output_dim = 6, init = 'uniform', activation = 'relu'))

# Adding the output layer
classifier.add(Dense(output_dim = 1, init = 'uniform', activation = 
'softmax'))

# Compiling the ANN
classifier.compile(optimizer = 'adam', loss = 'categorical_crossentropy', 
metrics = ['accuracy'])

# Fitting the ANN to the Training set
classifier.fit(X_train, y_train, batch_size = 10, nb_epoch = 50)

# Part 3 - Making the predictions and evaluating the model

# Predicting the Test set results
y_pred = classifier.predict(X_test)
y_pred = (y_pred > 0.5)

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

Answer 1

我假设你要预测的目标类是二元的，即只有 2 个可能的值会出现

如果你的目标是二进制的，那么模型的最后一层应该用sigmoid激活函数激活。此外，模型应该使用binary_crossentropy 或sparse_categorical_crossentropy 编译。

如果目标是多类的，即超过 2 个可能的值，您必须在 keras 的 to_categorical 的帮助下将目标转换为分类目标。然后你应该用categorical_crossentropy编译你的模型，模型中的最后一层应该用softmax激活函数激活。！！

Answer 2

问题在于你的这部分代码，

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_Y_1 = LabelEncoder()
yy = labelencoder_Y_1.fit_transform(yy)

您忘记对yy 进行一次热编码，请注意LabelEncoder 仅将您的分类数据转换为数字一，即[A, B, C, D, E, F, G] 到[1, 2, 3, 4, 5, 6, 7]。由于您想使用softmax 激活和categorical_crossentropy，因此您必须对其进行一次热编码（我过于简化了，但这是要点）。

所以，应该是这样的，

# Encoding categorical data
from keras.utils import to_categorical
from sklearn.preprocessing import LabelEncoder
labelencoder_Y_1 = LabelEncoder()
yy = labelencoder_Y_1.fit_transform(yy)
yy = to_categorical(yy)