Image processing Keras model.pop（）不工作

我正在使用Python 3.6.2和Tensorflow gpu 1.3.0运行Keras 2.0.6

为了对Vgg16模型进行微调，我在手工构建了Vgg16体系结构并加载权重后运行了这段代码，但我还没有调用compile（）：

当我在Tensorboard中查看图表时，我看到（查看所附图片的左上角）稠密的_3连接到辍学的_2，但它自己在悬挂。然后在它旁边我看到稠密的_4，也连接到辍学的_2

2016年5月6日，joelthchao建议我用下面的pop_layer（）代码替换pop（）。不幸的是，Tensorboard中显示的图形变得不可理解

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

我知道有些东西不能正常工作，因为我在Kaggle猫对狗比赛中运行这段代码时，精度很低，我在90%左右徘徊，而其他运行这段代码（它是从fast.ai改编的）的人在Theanos上很容易得到97%。也许我的精度问题来自其他地方，但我仍然不认为稠密_3应该悬挂在那里，我想知道这是否可能是我精度问题的根源

我怎样才能明确地断开并移除密集型_3

---

在运行代码以准备微调之前和之后，model.summary（）请参见下文。我们再也看不到稠密的_3了，但我们确实在张力板图中看到了它

跑步前

---

---

跑步后

---

我相信这是在使用tensorflow后端时在Keras中实现layers.pop（）的一个好方法。现在，这里有一个按名称删除最后一层的方法：

name_last_layer = str(model1.layers[-1])

model2 = Sequential()
for layer in model1.layers:
    if str(layer) != name_last_layer:
        model2.add(layer)

其中model1是原始模型，model2是没有最后一层的同一模型。在本例中，我将model2设置为一个顺序模型，但您当然可以更改它

Layer (type)                 Output Shape              Param #   
=================================================================
lambda_1 (Lambda)            (None, 3, 224, 224)       0         
_________________________________________________________________
zero_padding2d_1 (ZeroPaddin (None, 3, 226, 226)       0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 64, 224, 224)      1792      
_________________________________________________________________
zero_padding2d_2 (ZeroPaddin (None, 64, 226, 226)      0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 64, 224, 224)      36928     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 64, 112, 112)      0         
_________________________________________________________________
zero_padding2d_3 (ZeroPaddin (None, 64, 114, 114)      0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 128, 112, 112)     73856     
_________________________________________________________________
zero_padding2d_4 (ZeroPaddin (None, 128, 114, 114)     0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 128, 112, 112)     147584    
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 128, 56, 56)       0         
_________________________________________________________________
zero_padding2d_5 (ZeroPaddin (None, 128, 58, 58)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 256, 56, 56)       295168    
_________________________________________________________________
zero_padding2d_6 (ZeroPaddin (None, 256, 58, 58)       0         
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 256, 56, 56)       590080    
_________________________________________________________________
zero_padding2d_7 (ZeroPaddin (None, 256, 58, 58)       0         
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 256, 56, 56)       590080    
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 256, 28, 28)       0         
_________________________________________________________________
zero_padding2d_8 (ZeroPaddin (None, 256, 30, 30)       0         
_________________________________________________________________
conv2d_8 (Conv2D)            (None, 512, 28, 28)       1180160   
_________________________________________________________________
zero_padding2d_9 (ZeroPaddin (None, 512, 30, 30)       0         
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 512, 28, 28)       2359808   
_________________________________________________________________
zero_padding2d_10 (ZeroPaddi (None, 512, 30, 30)       0         
_________________________________________________________________
conv2d_10 (Conv2D)           (None, 512, 28, 28)       2359808   
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 512, 14, 14)       0         
_________________________________________________________________
zero_padding2d_11 (ZeroPaddi (None, 512, 16, 16)       0         
_________________________________________________________________
conv2d_11 (Conv2D)           (None, 512, 14, 14)       2359808   
_________________________________________________________________
zero_padding2d_12 (ZeroPaddi (None, 512, 16, 16)       0         
_________________________________________________________________
conv2d_12 (Conv2D)           (None, 512, 14, 14)       2359808   
_________________________________________________________________
zero_padding2d_13 (ZeroPaddi (None, 512, 16, 16)       0         
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 512, 14, 14)       2359808   
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 512, 7, 7)         0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 25088)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 4096)              102764544 
_________________________________________________________________
dropout_1 (Dropout)          (None, 4096)              0         
_________________________________________________________________
dense_2 (Dense)              (None, 4096)              16781312  
_________________________________________________________________
dropout_2 (Dropout)          (None, 4096)              0         
_________________________________________________________________
dense_3 (Dense)              (None, 1000)              4097000   
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lambda_1 (Lambda)            (None, 3, 224, 224)       0         
_________________________________________________________________
zero_padding2d_1 (ZeroPaddin (None, 3, 226, 226)       0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 64, 224, 224)      1792      
_________________________________________________________________
zero_padding2d_2 (ZeroPaddin (None, 64, 226, 226)      0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 64, 224, 224)      36928     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 64, 112, 112)      0         
_________________________________________________________________
zero_padding2d_3 (ZeroPaddin (None, 64, 114, 114)      0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 128, 112, 112)     73856     
_________________________________________________________________
zero_padding2d_4 (ZeroPaddin (None, 128, 114, 114)     0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 128, 112, 112)     147584    
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 128, 56, 56)       0         
_________________________________________________________________
zero_padding2d_5 (ZeroPaddin (None, 128, 58, 58)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 256, 56, 56)       295168    
_________________________________________________________________
zero_padding2d_6 (ZeroPaddin (None, 256, 58, 58)       0         
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 256, 56, 56)       590080    
_________________________________________________________________
zero_padding2d_7 (ZeroPaddin (None, 256, 58, 58)       0         
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 256, 56, 56)       590080    
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 256, 28, 28)       0         
_________________________________________________________________
zero_padding2d_8 (ZeroPaddin (None, 256, 30, 30)       0         
_________________________________________________________________
conv2d_8 (Conv2D)            (None, 512, 28, 28)       1180160   
_________________________________________________________________
zero_padding2d_9 (ZeroPaddin (None, 512, 30, 30)       0         
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 512, 28, 28)       2359808   
_________________________________________________________________
zero_padding2d_10 (ZeroPaddi (None, 512, 30, 30)       0         
_________________________________________________________________
conv2d_10 (Conv2D)           (None, 512, 28, 28)       2359808   
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 512, 14, 14)       0         
_________________________________________________________________
zero_padding2d_11 (ZeroPaddi (None, 512, 16, 16)       0         
_________________________________________________________________
conv2d_11 (Conv2D)           (None, 512, 14, 14)       2359808   
_________________________________________________________________
zero_padding2d_12 (ZeroPaddi (None, 512, 16, 16)       0         
_________________________________________________________________
conv2d_12 (Conv2D)           (None, 512, 14, 14)       2359808   
_________________________________________________________________
zero_padding2d_13 (ZeroPaddi (None, 512, 16, 16)       0         
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 512, 14, 14)       2359808   
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 512, 7, 7)         0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 25088)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 4096)              102764544 
_________________________________________________________________
dropout_1 (Dropout)          (None, 4096)              0         
_________________________________________________________________
dense_2 (Dense)              (None, 4096)              16781312  
_________________________________________________________________
dropout_2 (Dropout)          (None, 4096)              0         
_________________________________________________________________
dense_4 (Dense)              (None, 2)                 8194      
=================================================================
Total params: 134,268,738
Trainable params: 8,194
Non-trainable params: 134,260,544

name_last_layer = str(model1.layers[-1])

model2 = Sequential()
for layer in model1.layers:
    if str(layer) != name_last_layer:
        model2.add(layer)