Tensorflow 在兩個模型之間共享層

Question

讓我們的模型成為幾個全連接層：

我想共享中間層並使用兩個具有相同權重的模型，如下所示：

我可以用 Tensorflow 做這個嗎？

Answer 1

是的，您可以共享圖層！ 官方 TensorFlow 教程在這里。

在您的情況下，可以使用可變范圍實現層共享

#Create network starts, which are not shared
start_of_net1 = create_start_of_net1(my_inputs_for_net1)
start_of_net2 = create_start_of_net2(my_inputs_for_net2)

#Create shared middle layers
#Start by creating a middle layer for one of the networks in a variable scope
with tf.variable_scope("shared_middle", reuse=False) as scope:
    middle_of_net1 = create_middle(start_of_net1)
#Share the variables by using the same scope name and reuse=True
#when creating those layers for your other network
with tf.variable_scope("shared_middle", reuse=True) as scope:
    middle_of_net2 = create_middle(start_of_net2)

#Create end layers, which are not shared
end_of_net1 = create_end_of_net1(middle_of_net1)
end_of_net2 = create_end_of_net2(middle_of_net2)

一旦在變量范圍內創建了一個層，您可以根據需要多次重用該層中的變量。 在這里，我們只重用它們一次。