Keras - 每个时间步嵌入 2 个单词的 LSTM

Question

下面的代码构建了一个 LSTM 模型。 我想将这个确切的模型更改为在开始时有一个嵌入层，它在每个时间步接收 2 个不同的单词，嵌入它们（使用相同的嵌入层）：它连接它们的嵌入，然后遵循我的模型的其余部分.

k_model = Sequential()

k_model.add(LSTM(int(document_max_num_words*1.5), input_shape=(document_max_num_words, num_features)))
k_model.add(Dropout(0.3))
k_model.add(Dense(num_categories))
k_model.add(Activation('sigmoid'))

k_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Answer 1

如果我正确理解您的问题，假设输入数据的形状为 (n_samples, n_timesteps, 2)（即每步两个字），您可以使用 TimeDistributed 包装器实现您想要的：

from keras import layers
from keras import models

n_vocab = 1000
n_timesteps = 500
embed_dim = 128
words_per_step = 2

model = models.Sequential()
model.add(layers.TimeDistributed(layers.Embedding(n_vocab, embed_dim), input_shape=(n_timesteps, words_per_step)))
model.add(layers.TimeDistributed(layers.Flatten()))
# the rest of the model

model.summary()

模型总结：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
time_distributed_12 (TimeDis (None, 500, 2, 128)       128000    
_________________________________________________________________
time_distributed_13 (TimeDis (None, 500, 256)          0         
=================================================================
Total params: 128,000
Trainable params: 128,000
Non-trainable params: 0
_________________________________________________________________