我正在尝试使用 CNN 进行情感分析
我的代码我的数据具有 (1000,1000) 形状,当我将数据传递给 convolution2D 时,它会抛出一个错误。我无法解决。
我尝试了以下解决方案,但仍然面临问题。在构建 CNN 时,我收到 Keras 的抱怨,这些抱怨对我来说毫无意义。 https://stackoverflow.com/questions/37085653/when-bulding-a-cnn-i-am-getting-complaints-from-keras-that-do-not-make-sense-to
我的代码如下。
TfIdf = TfidfVectorizer(max_features=1000)
X = TfIdf.fit_transform(x.ravel())
Y = df.iloc[:,1:2].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2,random_state=1)
classifier = Sequential()
classifier.add(Convolution2D(32, kernel_size=(3,3), input_shape=(1000, 1000, 1), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size=(2,2)))
classifier.add(Flatten())
classifier.add(Dense(output_dim = 128, activation='relu'))
classifier.add(Dense(output_dim = 1, activation='sigmoid'))
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
classifier.fit(X_train, Y_train, batch_size = 10, nb_epoch = 100, validation_data=(X_test,Y_test))
(loss,accuracy) = classifier.evaluate(X_test,Y_test, batch_size =10)
print(accuracy)