在 keras 中使用 LSTM 对序列进行分类

Question

我正在研究一个二元分类问题，其中网络接受两个输入并输出这个输入对的标签。

基本上，我首先使用编码器层进行嵌入并将嵌入结果连接起来。接下来，我将使用 RNN 结构对级联结果进行分类。但是我想不出编写代码的正确方法。我在下面附上我的代码。

input_size = n_feature # the number of features
encoder_size = 2000 # output dim for each encoder
dropout_rate = 0.5 
X1 = Input(shape=(input_size, ), name='input_1')
X2 = Input(shape=(input_size, ), name='input_2')

encoder = Sequential()
encoder.add(Dropout(dropout_rate, input_shape=(input_size, )))
encoder.add(Dense(encoder_size, activation='relu'))

encoded_1 = encoder(X1)
encoded_2 = encoder(X2)
merged = concatenate([encoded_1, encoded_2])

#----------Need Help---------------#
comparer = Sequential()
comparer.add(LSTM(512, input_shape=(encoder_size*2, ), return_sequences=True))
comparer.add(Dropout(dropout_rate))
comparer.add(TimeDistributed(Dense(1)))
comparer.add(Activation('sigmoid'))
#----------Need Help---------------#

Y = comparer(merged)
model = Model(inputs=[X1, X2], outputs=Y)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

似乎对于 LSTM 层，输入应该是(None, encoder_size*2)。我尝试使用Y = comparer(K.transpose(merged)) 重塑 LSTM 层的输入，但失败了。顺便说一句，对于这个网络，输入形状是(input_size,)，输出形状是(1,)。

Answer 1

如果想法是按时间序列转换输入向量，您可以简单地对其进行重塑：

comparer = Sequential()

#reshape the vector into a time series form: (None, timeSteps, features)
comparer.add(Reshape((2 * encoder_size,1), input_shape=(2*encoder_size,))

#don't return sequences, you don't want a sequence as result:
comparer.add(LSTM(512, return_sequences=False))

comparer.add(Dropout(dropout_rate))

#Don't use a TimeDistributed, you're not dealing with a series anymore  
comparer.add(Dense(1))

comparer.add(Activation('sigmoid'))