AttributeError：“Sequential”对象没有“”score“”属性“”

Question

我正在使用卷积神经网络，而使用顺序训练数据时遇到了问题。使用顺序是不可能得到最好的分数吗？？

from numpy import array
from numpy import reshape
import numpy as np
def model_CNN(X_train,Y_train,X_test,Y_test):

    model = Sequential()

    model.add(Conv1D(filters=512, kernel_size=32, padding='same', kernel_initializer='normal', activation='relu', input_shape=(256, 1)))
    model.add(Conv1D(filters=512, kernel_size=32, padding='same', kernel_initializer='normal', activation='relu'))
    model.add(Dropout(0.2)) # This is the dropout layer. It's main function is to inactivate 20% of neurons in order to prevent overfitting
    model.add(Conv1D(filters=256, kernel_size=32, padding='same', kernel_initializer='normal', activation='relu'))
    model.add(Dropout(0.2))
    model.add(Conv1D(filters=256, kernel_size=32, padding='same', kernel_initializer='normal', activation='relu'))

    model.add(Flatten())

    optimizer = keras.optimizers.SGD(lr=0.01, momentum=0.5)
    model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy'])
    convolutional_model = model.fit(X_train, Y_train, epochs=5,batch_size=64,verbose=1, validation_data=(X_test, Y_test))
    print(convolutional_model.score(X_train,Y_train))
    model.summary()
    return model

作为错误接收的回溯：

AttributeError                            Traceback (most recent call last)
<ipython-input-50-9a2005301144> in <module>()
      1 
----> 2 convolutional_model= model_CNN(X_train,Y_train,X_test,Y_test)
      3 print(convolutional_model)

<ipython-input-49-bac0ec08f100> in model_CNN(X_train, Y_train, X_test, Y_test)
     34     model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy'])
     35     convolutional_model = model.fit(X_train, Y_train, epochs=5,batch_size=64,verbose=1, validation_data=(X_test, Y_test))
---> 36     print(convolutional_model.score(X_train,Y_train))
     37     # Print the summary of the model
     38     model.summary()

AttributeError: 'Sequential' object has no attribute 'score'

由于我是python的新手，我遇到了麻烦，并查看了各种资源，但都没有帮助，请指导我…我从这一行得到了错误

print(convolutional_model.score(X_train,Y_train))

如果不可能，请指导我找一个更好的…

Answer 1

您应该使用model而不是convolutional_model对象。fit函数返回一个历史对象，其中包含有关训练阶段的一些信息，如损失、准确性。这取决于你的损失函数和度量函数。

你能试试这个吗？

print(model.evaluate(X_train, Y_train))