Python 连接层在Keras多任务中做什么？

我正在Keras中实现一个简单的多任务模型。我使用了共享层标题下的中给出的代码

我知道，在多任务学习中，我们共享模型中的一些初始层，最后的层根据具体任务的不同而不同

在kerasapi中有以下两种情况，第一种情况下，我使用

keras.layers.concatenate

，而在另一种情况下，我不使用任何

keras.layers.concatenate

我张贴的代码以及每个案件的模式如下

案例1代码

import keras
from keras.layers import Input, LSTM, Dense
from keras.models import Model
from keras.models import Sequential
from keras.layers import Dense
from keras.utils.vis_utils import plot_model

tweet_a = Input(shape=(280, 256))
tweet_b = Input(shape=(280, 256))

# This layer can take as input a matrix
# and will return a vector of size 64
shared_lstm = LSTM(64)

# When we reuse the same layer instance
# multiple times, the weights of the layer
# are also being reused
# (it is effectively *the same* layer)
encoded_a = shared_lstm(tweet_a)
encoded_b = shared_lstm(tweet_b)

# We can then concatenate the two vectors:
merged_vector = keras.layers.concatenate([encoded_a, encoded_b], axis=-1)

# And add a logistic regression on top
predictions1 = Dense(1, activation='sigmoid')(merged_vector)
predictions2 = Dense(1, activation='sigmoid')(merged_vector)

# We define a trainable model linking the
# tweet inputs to the predictions
model = Model(inputs=[tweet_a, tweet_b], outputs=[predictions1, predictions2])

model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

import keras
from keras.layers import Input, LSTM, Dense
from keras.models import Model
from keras.models import Sequential
from keras.layers import Dense
from keras.utils.vis_utils import plot_model

tweet_a = Input(shape=(280, 256))
tweet_b = Input(shape=(280, 256))

# This layer can take as input a matrix
# and will return a vector of size 64
shared_lstm = LSTM(64)

# When we reuse the same layer instance
# multiple times, the weights of the layer
# are also being reused
# (it is effectively *the same* layer)
encoded_a = shared_lstm(tweet_a)
encoded_b = shared_lstm(tweet_b)



# And add a logistic regression on top
predictions1 = Dense(1, activation='sigmoid')(encoded_a )
predictions2 = Dense(1, activation='sigmoid')(encoded_b)

# We define a trainable model linking the
# tweet inputs to the predictions
model = Model(inputs=[tweet_a, tweet_b], outputs=[predictions1, predictions2])

model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

案例1模型

案例2代码

import keras
from keras.layers import Input, LSTM, Dense
from keras.models import Model
from keras.models import Sequential
from keras.layers import Dense
from keras.utils.vis_utils import plot_model

tweet_a = Input(shape=(280, 256))
tweet_b = Input(shape=(280, 256))

# This layer can take as input a matrix
# and will return a vector of size 64
shared_lstm = LSTM(64)

# When we reuse the same layer instance
# multiple times, the weights of the layer
# are also being reused
# (it is effectively *the same* layer)
encoded_a = shared_lstm(tweet_a)
encoded_b = shared_lstm(tweet_b)

# We can then concatenate the two vectors:
merged_vector = keras.layers.concatenate([encoded_a, encoded_b], axis=-1)

# And add a logistic regression on top
predictions1 = Dense(1, activation='sigmoid')(merged_vector)
predictions2 = Dense(1, activation='sigmoid')(merged_vector)

# We define a trainable model linking the
# tweet inputs to the predictions
model = Model(inputs=[tweet_a, tweet_b], outputs=[predictions1, predictions2])

model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

import keras
from keras.layers import Input, LSTM, Dense
from keras.models import Model
from keras.models import Sequential
from keras.layers import Dense
from keras.utils.vis_utils import plot_model

tweet_a = Input(shape=(280, 256))
tweet_b = Input(shape=(280, 256))

# This layer can take as input a matrix
# and will return a vector of size 64
shared_lstm = LSTM(64)

# When we reuse the same layer instance
# multiple times, the weights of the layer
# are also being reused
# (it is effectively *the same* layer)
encoded_a = shared_lstm(tweet_a)
encoded_b = shared_lstm(tweet_b)



# And add a logistic regression on top
predictions1 = Dense(1, activation='sigmoid')(encoded_a )
predictions2 = Dense(1, activation='sigmoid')(encoded_b)

# We define a trainable model linking the
# tweet inputs to the predictions
model = Model(inputs=[tweet_a, tweet_b], outputs=[predictions1, predictions2])

model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

案例2模型

在这两种情况下，仅共享

LSTM

层。在案例1中，我们有

keras.layers.concatenate

，但在案例2中，我们没有任何

keras.layers.concatenate

---

我的问题是，哪一个是多任务，案例1还是案例2？此外，在案例1中，

keras.layers.concatenate

的功能是什么？

都是多任务模型，因为这仅取决于是否有多个输出，每个输出关联一个任务

<>差异在于你的第一个模型明确地连接了共享层产生的特征，所以两个输出任务都可以考虑来自两个输入的信息。第二个模型仅从一个输入直接连接到一个输出，而不考虑其他输入。这里模型之间的唯一联系是它们共享LSTM权重