Question

下面的代码构造了一个LSTM模型。我想更改此精确模型，使其在开始时具有一个嵌入层，该层在每个时间步骤接收2个不同的单词，然后将它们嵌入（具有相同的嵌入层）：将它们的嵌入连接起来，然后遵循我的模型其余部分

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

如果我正确理解了您的问题，假设输入数据的形状为(n_samples, n_timesteps, 2)（即每步两个单词），则可以使用TimeDistributed包装器来实现您要查找的内容：

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()

模型摘要：

_________________________________________________________________
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
_________________________________________________________________

Keras-LSTM，每个时间步都有2个单词的嵌入

1 个答案: