特征与Keras预先训练CNN模型

Question

我有一个简单CNN模型看起来像这样：

_________________________________________________________________ 
Layer (type)     Output Shape    Param # 
================================================================= 
conv2d_1 (Conv2D)   (None, 26, 26, 32)  320  
_________________________________________________________________ 
conv2d_2 (Conv2D)   (None, 24, 24, 64)  18496  
_________________________________________________________________ 
max_pooling2d_1 (MaxPooling2 (None, 12, 12, 64)  0   
_________________________________________________________________ 
dropout_1 (Dropout)   (None, 12, 12, 64)  0   
_________________________________________________________________ 
flatten_1 (Flatten)   (None, 9216)    0   
_________________________________________________________________ 
dense_1 (Dense)    (None, 128)    1179776 
_________________________________________________________________ 
dropout_2 (Dropout)   (None, 128)    0   
_________________________________________________________________ 
dense_2 (Dense)    (None, 10)    1290  
================================================================= 
Total params: 1,199,882.0 
Trainable params: 1,199,882.0 
Non-trainable params: 0.0 
_________________________________________________________________ 

我弹出dense_2（SOFTMAX层）和dropout_2层以从提取特征图片：

（我使用自定义弹出功能这里提出：https://github.com/fchollet/keras/issues/2640）

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 

跳跳的最后两个层次：

pop_layer(model) 
pop_layer(model) 

之后，这样做model.summary()：

_________________________________________________________________ 
Layer (type)     Output Shape    Param # 
================================================================= 
conv2d_1 (Conv2D)   (None, 26, 26, 32)  320  
_________________________________________________________________ 
conv2d_2 (Conv2D)   (None, 24, 24, 64)  18496  
_________________________________________________________________ 
max_pooling2d_1 (MaxPooling2 (None, 12, 12, 64)  0   
_________________________________________________________________ 
dropout_1 (Dropout)   (None, 12, 12, 64)  0   
_________________________________________________________________ 
flatten_1 (Flatten)   (None, 9216)    0   
_________________________________________________________________ 
dense_1 (Dense)    (None, 128)    1179776 
================================================================= 
Total params: 1,198,592.0 
Trainable params: 1,198,592.0 
Non-trainable params: 0.0 
_________________________________________________________________ 

最后两层从模型中杀出，但是当我做了预测：

predictions = model.predict(x_test) 
print(len(predictions[0])) 

10 

正如你可以看到输出仍然是softmax，是我做错了什么？

谢谢！

Answer 1

事实证明，您需要build或compile模型在pop层之后才能使您的模型正常工作。