Keras Functional API:LTSM 返回一个二维数组

Question

我是stack，我需要stackoverflow的智慧。

我有一个使用函数式 API在 Keras 中实现的双输入神经网络，输入形状是：

X.shape, X_size.shape, y.shape
((123, 9), (123, 2), (123, 9, 10))

所以，我的问题是我想从 LSTM 获得具有 3D 形状的输出形状，以便使用我的y张量。我知道，我可以将我的 y重塑为 2-D 形状，但我想将其用作 3-D 数组。

from keras.models import Model
from keras import layers
from keras import Input
# first input 
list_input = Input(shape=(None,), dtype='int32', name='li')
embedded_list = layers.Embedding(100,90)(list_input)
encoded_list = layers.LSTM(4,  name = "lstm1")(embedded_list)
# second input 
size_input = Input(shape=(None,), dtype='int32', name='si')
embedded_size = layers.Embedding(100,10)(size_input)
encoded_size = layers.LSTM(4, name = "lstm2")(embedded_size)
# concatenate
concatenated = layers.concatenate([encoded_size, encoded_list], axis=-1)
answer = layers.Dense(90, activation='sigmoid', name = 'outpuy_layer')(concatenated)

model = Model([list_input, size_input], answer)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=[f1])

模型摘要：

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
si (InputLayer)                  (None, None)          0                                            
____________________________________________________________________________________________________
li (InputLayer)                  (None, None)          0                                            
____________________________________________________________________________________________________
embedding_16 (Embedding)         (None, None, 10)      1000        si[0][0]                         
____________________________________________________________________________________________________
embedding_15 (Embedding)         (None, None, 90)      9000        li[0][0]                         
____________________________________________________________________________________________________
lstm2 (LSTM)                     (None, 4)             240         embedding_16[0][0]               
____________________________________________________________________________________________________
lstm1 (LSTM)                     (None, 4)             1520        embedding_15[0][0]               
____________________________________________________________________________________________________
concatenate_8 (Concatenate)      (None, 8)             0           lstm2[0][0]                      
lstm1[0][0]                      
____________________________________________________________________________________________________
outpuy_layer (Dense)             (None, 90)            810         concatenate_8[0][0]              
====================================================================================================
Total params: 12,570
Trainable params: 12,570
Non-trainable params: 0

再一次，问题是：

如何从 LSTM 获得输出形状，例如(无、无、无/10(？

Answer 1

Keras 默认忽略每个时间步输出，最后一个输出除外，这会创建一个 2D 数组。要获取 3D 数组(意味着您获得每个时间步的输出(，请将return_sequences设置为True实例化该层。例如，在您的情况下：

encoded_list = layers.LSTM(4,  name = "lstm1", return_sequences=True)(embedded_list)