Keras - Pop and add layers, but the layer does not turn off

Question

Using Keras (1.2.2), I load a sequential model, the last layers of which:

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

Then I want to output the last layer, add another fully connected layer and add the classification layer again.

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())

As you can see, my dense_3 and activ_7 were not connected to the network (empty value in the summary () with "Connected to"). I can not find anything in the documentation that explains how to solve this problem. Any ideas?

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]                    
====================================================================================================

Following the answer below, I compiled the model before printing model.summary(), but for some reason the layers were not selected correctly, as the summary shows: the last level connections are incorrect:

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]                    
====================================================================================================

But it must be

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

, , - .

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

, .

:

, , Sequential. , ( , , , - ) :

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())

, layer1.input layer1.output, .

API-. , .

pop(), , , github:

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

. :

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()

, , , , , .

, .

Answer 2

- , , .

conda list keras
# Name                    Version                   Build  Channel
keras                     2.1.5                    py36_0    conda-forge

:

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

    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

def get_model():
    #Fully convolutional part of VGG16
    model = VGG16(include_top=False, weights='imagenet')

    #Remove last max pooling layer
    pop_layer(model)

    #Freeze pretrained layers
    for layer in model.layers:
        layer.trainable = False

    model = Model(inputs=model.inputs, outputs=model.outputs)

    print('len(model.layers)', len(model.layers)) #
    print(model.summary()) #

    x = GlobalAveragePooling2D()(model.output)
    head = Dense(N_CLASS, activation='softmax')(x)

    model = Model(inputs=model.inputs, outputs=head)

    model.compile(optimizer=Adadelta(), loss='categorical_crossentropy', metrics=['accuracy'])

    print('len(model.layers)', len(model.layers)) #
    print(model.summary()) #

    return model