TensorFlow 在两个模型之间共享层

Question

让我们的模型成为几个全连接层：

我想共享中间层并使用两个具有相同权重的模型，如下所示：

我可以用 Tensorflow 做这个吗？

Answer 1

是的，您可以共享图层！ TensorFlow 官方教程是here。

在您的情况下，可以使用可变范围实现层共享

#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)

在变量范围内创建层后，您可以根据需要多次重复使用该层中的变量。在这里，我们只重用它们一次。