如何在Keras Python中使用带有LSTM的TF IDF矢量化器

Question

我正在尝试在Python的Keras库中使用LSTM训练Seq2Seq模型。我想使用句子的TF IDF矢量表示作为模型的输入并得到错误。

X = ["Good morning", "Sweet Dreams", "Stay Awake"]
Y = ["Good morning", "Sweet Dreams", "Stay Awake"]

vectorizer = TfidfVectorizer()
vectorizer.fit(X)
vectorizer.transform(X)
vectorizer.transform(Y)
tfidf_vector_X = vectorizer.transform(X).toarray() #shape - (3,6)
tfidf_vector_Y = vectorizer.transform(Y).toarray() #shape - (3,6)
tfidf_vector_X = tfidf_vector_X[:, :, None] #shape - (3,6,1) since LSTM cells expects ndims = 3
tfidf_vector_Y = tfidf_vector_Y[:, :, None] #shape - (3,6,1)

X_train, X_test, y_train, y_test = train_test_split(tfidf_vector_X, tfidf_vector_Y, test_size = 0.2, random_state = 1)
model = Sequential()
model.add(LSTM(output_dim = 6, input_shape = X_train.shape[1:], return_sequences = True, init = 'glorot_normal', inner_init = 'glorot_normal', activation = 'sigmoid'))
model.add(LSTM(output_dim = 6, input_shape = X_train.shape[1:], return_sequences = True, init = 'glorot_normal', inner_init = 'glorot_normal', activation = 'sigmoid'))
model.add(LSTM(output_dim = 6, input_shape = X_train.shape[1:], return_sequences = True, init = 'glorot_normal', inner_init = 'glorot_normal', activation = 'sigmoid'))
model.add(LSTM(output_dim = 6, input_shape = X_train.shape[1:], return_sequences = True, init = 'glorot_normal', inner_init = 'glorot_normal', activation = 'sigmoid'))
adam = optimizers.Adam(lr = 0.001, beta_1 = 0.9, beta_2 = 0.999, epsilon = None, decay = 0.0, amsgrad = False)
model.compile(loss = 'cosine_proximity', optimizer = adam, metrics = ['accuracy'])
model.fit(X_train, y_train, nb_epoch = 100)

上面的代码抛出：

Error when checking target: expected lstm_4 to have shape (6, 6) but got array with shape (6, 1)

有人能告诉我什么是错的以及如何解决它？

Answer 1

如上图所示，网络期望最终层作为输出层。您必须将最终图层的尺寸作为输出尺寸。

在您的情况下，它将是行数* 1，如错误（6,1）中所示是您的维度。

在最后一层中将输出维度更改为1

使用keras，您可以设计自己的网络。因此，您应该负责使用输出层创建端到端隐藏层。

Answer 2

目前，您将在最后一层返回维度6的序列。您可能希望返回维度序列1以匹配您的目标序列。我不是百分百肯定，因为我对seq2seq模型没有经验，但至少代码以这种方式运行。也许看看Keras blog上的seq2seq教程。

除此之外，还有两点：使用Sequential API时，您只需要为模型的第一层指定input_shape。此外，output_dim图层的LSTM参数已弃用，应替换为units参数：

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split

X = ["Good morning", "Sweet Dreams", "Stay Awake"]
Y = ["Good morning", "Sweet Dreams", "Stay Awake"]

vectorizer = TfidfVectorizer().fit(X)

tfidf_vector_X = vectorizer.transform(X).toarray()  #//shape - (3,6)
tfidf_vector_Y = vectorizer.transform(Y).toarray() #//shape - (3,6)
tfidf_vector_X = tfidf_vector_X[:, :, None] #//shape - (3,6,1) 
tfidf_vector_Y = tfidf_vector_Y[:, :, None] #//shape - (3,6,1)

X_train, X_test, y_train, y_test = train_test_split(tfidf_vector_X, tfidf_vector_Y, test_size = 0.2, random_state = 1)

from keras import Sequential
from keras.layers import LSTM

model = Sequential()
model.add(LSTM(units=6, input_shape = X_train.shape[1:], return_sequences = True))
model.add(LSTM(units=6, return_sequences=True))
model.add(LSTM(units=6, return_sequences=True))
model.add(LSTM(units=1, return_sequences=True, name='output'))
model.compile(loss='cosine_proximity', optimizer='sgd', metrics = ['accuracy'])

print(model.summary())

model.fit(X_train, y_train, epochs=1, verbose=1)