如何从预训练模型中删除最后一层。我尝试过 model.layers.pop() 但它不起作用

Question

我正在尝试删除最后一层，以便我可以使用转移学习。

vgg16_model = keras.applications.vgg16.VGG16()
model = Sequential()

for layer in vgg16_model.layers:
    model.add(layer)

model.layers.pop()


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


# Add 'softmax' instead of earlier 'prediction' layer.
model.add(Dense(2, activation='softmax'))


# Check the summary, and yes new layer has been added. 
model.summary()

但我得到的输出并不是我所期望的。仍然显示的是vgg16模型的最后一层。

这是输出

    _________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
block1_conv1 (Conv2D)        (None, 224, 224, 64)      1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 224, 224, 64)      36928       

**THE HIDDEN LAYERS** 
_________________________________________________________________
fc1 (Dense)                  (None, 4096)              102764544 
_________________________________________________________________
fc2 (Dense)                  (None, 4096)              16781312  
_________________________________________________________________
predictions (Dense)          (None, 1000)              4097000   
_________________________________________________________________
dense_10 (Dense)             (None, 2)                 2002      
=================================================================
Total params: 138,359,546
Trainable params: 2,002
Non-trainable params: 138,357,544

注意- 在输出中我没有显示整个模型，只显示了前几层和最后几层。

我应该如何删除最后一层来进行迁移学习？

PS Keras 版本 = 2.2.4

Answer 1

只是首先不要将最后一层添加到模型中。这样你甚至不需要pop

vgg16_model = keras.applications.vgg16.VGG16()
model = Sequential()

for layer in vgg16_model.layers[:-1]: # this is where I changed your code
    model.add(layer)    

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

# Add 'softmax' instead of earlier 'prediction' layer.
model.add(Dense(2, activation='softmax'))