python - Keras - 弹出并重新添加图层，但图层不会断开连接

Question

使用 Keras (1.2.2)，我正在加载一个顺序模型，其最后一层是:

model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

然后，我想弹出最后一层，添加另一个全连接层，并重新添加分类层。

model = load_model('model1.h5')                                                                         
layer1 = model.layers.pop() # Copy activation_6 layer                                      
layer2 = model.layers.pop() # Copy classification layer (dense_2)                          

model.add(Dense(512, name='dense_3'))
model.add(Activation('softmax', name='activation_7'))

model.add(layer2)
model.add(layer1)

print(model.summary())

如您所见，我的dense_3 和activation_7 未连接到网络(summary() 中的值为“已连接到”的空值)。我在文档中找不到任何解释如何解决此问题的内容。有什么想法吗？

dense_1 (Dense)                  (None, 512)           131584      flatten_1[0][0]                  
____________________________________________________________________________________________________
activation_5 (Activation)        (None, 512)           0           dense_1[0][0]                    
____________________________________________________________________________________________________
dense_3 (Dense)                  (None, 512)           5632                                         
____________________________________________________________________________________________________
activation_7 (Activation)        (None, 512)           0                                            
____________________________________________________________________________________________________
dense_2 (Dense)                  (None, 10)            5130        activation_5[0][0]               
____________________________________________________________________________________________________
activation_6 (Activation)        (None, 10)            0           dense_2[0][0]                    
====================================================================================================

按照下面的答案，我在打印 model.summary() 之前编译了模型，但由于某些原因，层未正确弹出，如摘要所示:最后一层的连接错误的是:

dense_1 (Dense)                  (None, 512)           131584      flatten_1[0][0]                  
____________________________________________________________________________________________________
activation_5 (Activation)        (None, 512)           0           dense_1[0][0]                    
____________________________________________________________________________________________________
dense_3 (Dense)                  (None, 512)           5632        activation_6[0][0]               
____________________________________________________________________________________________________
activation_7 (Activation)        (None, 512)           0           dense_3[0][0]                    
____________________________________________________________________________________________________
dense_2 (Dense)                  (None, 10)            5130        activation_5[0][0]               
                                                                   activation_7[0][0]               
____________________________________________________________________________________________________
activation_6 (Activation)        (None, 10)            0           dense_2[0][0]                    
                                                                   dense_2[1][0]                    
====================================================================================================

但应该是

dense_1 (Dense)                  (None, 512)           131584      flatten_1[0][0]                  
____________________________________________________________________________________________________
activation_5 (Activation)        (None, 512)           0           dense_1[0][0]                    
____________________________________________________________________________________________________
dense_3 (Dense)                  (None, 512)           5632        activation_5[0][0]               
____________________________________________________________________________________________________
activation_7 (Activation)        (None, 512)           0           dense_3[0][0]                    
____________________________________________________________________________________________________
dense_2 (Dense)                  (None, 10)            5130                       
                                                                   activation_7[0][0]               
____________________________________________________________________________________________________
activation_6 (Activation)        (None, 10)            0           dense_2[0][0]                    

====================================================================================================

Answer 1

当您删除图层时，您需要重新编译模型才能使其生效。

所以使用

model.compile(loss=...,optimizer=..., ...)

在打印摘要之前，它应该正确集成更改。

编辑:

对于顺序模式，您想要做的事情实际上非常复杂。这是我可以为您的顺序模型提出的解决方案(如果有更好的请告诉我):

model = load_model('model1.h5')                                                                         
layer1 = model.layers.pop() # Copy activation_6 layer                                      
layer2 = model.layers.pop() # Copy classification layer (dense_2)                          

model.add(Dense(512, name='dense_3'))
model.add(Activation('softmax', name='activation_7'))

# get layer1 config
layer1_config = layer1.get_config()
layer2_config = layer2.get_config()
# change the name of the layers otherwise it complains
layer1_config['name'] = layer1_config['name'] + '_new'
layer2_config['name'] = layer2_config['name'] + '_new'

# import the magic function
from keras.utils.layer_utils import layer_from_config
# re-add new layers from the config of the old ones 
model.add(layer_from_config({'class_name':type(l2), 'config':layer2_config}))
model.add(layer_from_config({'class_name':type(l1), 'config':layer1_config}))

model.compile(...)

print(model.summary())

问题在于，您的图层具有我无法更改的 layer1.input 和 layer1.output 属性。

解决这个问题的方法是使用函数式 API 模型。这使您可以定义层中的内容进来和出去。

首先，您需要定义 pop() 函数，以便在每次弹出图层时正确重新链接图层，该函数来自 this github issue :

def pop_layer(model):
    if not model.outputs:
        raise Exception('Sequential model cannot be popped: model is empty.')

    popped_layer = model.layers.pop()
    if not model.layers:
        model.outputs = []
        model.inbound_nodes = []
        model.outbound_nodes = []
    else:
        model.layers[-1].outbound_nodes = []
        model.outputs = [model.layers[-1].output]
    model.built = False
    return popped_layer

它只是删除最后一层的每个输出链接，并将模型的输出更改为新的最后一层。现在您可以在以下位置使用它:

model = load_model('model1.h5')                                                                         
layer1 = model.layers.pop() # Copy activation_6 layer                                      
layer2 = model.layers.pop() # Copy classification layer (dense_2)     

# take model.outputs and feed a Dense layer
h = Dense(512,name='dense_3')(model.outputs)
h = Activation('relu', name=('activation_7')(h)
# apply
h = layer2(h)
output = layer1(h)

model = Model(input=model.input, output=output)
model.compile(...)
model.summary()

可能有比这更好的解决方案，但这就是我要做的。

我希望这会有所帮助。