在 Keras 中将 VGG 功能模型转换为顺序模型答案

【问题标题】：converting VGG functional model into sequential model in Keras在 Keras 中将 VGG 功能模型转换为顺序模型
【发布时间】：2017-10-01 23:47:18
【问题描述】：

我实际上是在尝试使用 Keras 获得 VGG16 的序列模型版本。功能版本可以通过以下方式获得：

from __future__ import division, print_function

import os, json
from glob import glob
import numpy as np
from scipy import misc, ndimage
from scipy.ndimage.interpolation import zoom

from keras import backend as K
from keras.layers.normalization import BatchNormalization
from keras.utils.data_utils import get_file
from keras.models import Sequential
from keras.layers.core import Flatten, Dense, Dropout, Lambda
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.layers.pooling import GlobalAveragePooling2D
from keras.optimizers import SGD, RMSprop, Adam
from keras.preprocessing import image
import keras   
import keras.applications.vgg16
from  keras.layers import Input

input_tensor = Input(shape=(224,224,3))
VGG_model=keras.applications.vgg16.VGG16(weights='imagenet',include_top= True,input_tensor=input_tensor)

总结如下：

VGG_model.summary()

Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_1 (InputLayer)             (None, 224, 224, 3)   0                                            
____________________________________________________________________________________________________
block1_conv1 (Convolution2D)     (None, 224, 224, 64)  1792        input_1[0][0]                    
____________________________________________________________________________________________________
block1_conv2 (Convolution2D)     (None, 224, 224, 64)  36928       block1_conv1[0][0]               
____________________________________________________________________________________________________
block1_pool (MaxPooling2D)       (None, 112, 112, 64)  0           block1_conv2[0][0]               
____________________________________________________________________________________________________
block2_conv1 (Convolution2D)     (None, 112, 112, 128) 73856       block1_pool[0][0]                
____________________________________________________________________________________________________
block2_conv2 (Convolution2D)     (None, 112, 112, 128) 147584      block2_conv1[0][0]               
____________________________________________________________________________________________________
block2_pool (MaxPooling2D)       (None, 56, 56, 128)   0           block2_conv2[0][0]               
____________________________________________________________________________________________________
block3_conv1 (Convolution2D)     (None, 56, 56, 256)   295168      block2_pool[0][0]                
____________________________________________________________________________________________________
block3_conv2 (Convolution2D)     (None, 56, 56, 256)   590080      block3_conv1[0][0]               
____________________________________________________________________________________________________
block3_conv3 (Convolution2D)     (None, 56, 56, 256)   590080      block3_conv2[0][0]               
____________________________________________________________________________________________________
block3_pool (MaxPooling2D)       (None, 28, 28, 256)   0           block3_conv3[0][0]               
____________________________________________________________________________________________________
block4_conv1 (Convolution2D)     (None, 28, 28, 512)   1180160     block3_pool[0][0]                
____________________________________________________________________________________________________
block4_conv2 (Convolution2D)     (None, 28, 28, 512)   2359808     block4_conv1[0][0]               
____________________________________________________________________________________________________
block4_conv3 (Convolution2D)     (None, 28, 28, 512)   2359808     block4_conv2[0][0]               
____________________________________________________________________________________________________
block4_pool (MaxPooling2D)       (None, 14, 14, 512)   0           block4_conv3[0][0]               
____________________________________________________________________________________________________
block5_conv1 (Convolution2D)     (None, 14, 14, 512)   2359808     block4_pool[0][0]                
____________________________________________________________________________________________________
block5_conv2 (Convolution2D)     (None, 14, 14, 512)   2359808     block5_conv1[0][0]               
____________________________________________________________________________________________________
block5_conv3 (Convolution2D)     (None, 14, 14, 512)   2359808     block5_conv2[0][0]               
____________________________________________________________________________________________________
block5_pool (MaxPooling2D)       (None, 7, 7, 512)     0           block5_conv3[0][0]               
____________________________________________________________________________________________________
flatten (Flatten)                (None, 25088)         0           block5_pool[0][0]                
____________________________________________________________________________________________________
fc1 (Dense)                      (None, 4096)          102764544   flatten[0][0]                    
____________________________________________________________________________________________________
fc2 (Dense)                      (None, 4096)          16781312    fc1[0][0]                        
____________________________________________________________________________________________________
predictions (Dense)              (None, 1000)          4097000     fc2[0][0]                        
====================================================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
____________________________________________________________________________________________________

根据这个网站https://github.com/fchollet/keras/issues/3190，它说

Sequential(layers=functional_model.layers)

可以将功能模型转换为顺序模型。但是，如果我这样做：

model = Sequential(layers=VGG_model.layers)
model.summary()

它导致

Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_1 (InputLayer)             (None, 224, 224, 3)   0                                            
____________________________________________________________________________________________________
block1_conv1 (Convolution2D)     (None, 224, 224, 64)  1792        input_1[0][0]                    
                                                                   input_1[0][0]                    
                                                                   input_1[0][0]                    
____________________________________________________________________________________________________
block1_conv2 (Convolution2D)     (None, 224, 224, 64)  36928       block1_conv1[0][0]               
                                                                   block1_conv1[1][0]               
                                                                   block1_conv1[2][0]               
____________________________________________________________________________________________________
block1_pool (MaxPooling2D)       (None, 112, 112, 64)  0           block1_conv2[0][0]               
                                                                   block1_conv2[1][0]               
                                                                   block1_conv2[2][0]               
____________________________________________________________________________________________________
block2_conv1 (Convolution2D)     (None, 112, 112, 128) 73856       block1_pool[0][0]                
                                                                   block1_pool[1][0]                
                                                                   block1_pool[2][0]                
____________________________________________________________________________________________________
block2_conv2 (Convolution2D)     (None, 112, 112, 128) 147584      block2_conv1[0][0]               
                                                                   block2_conv1[1][0]               
                                                                   block2_conv1[2][0]               
____________________________________________________________________________________________________
block2_pool (MaxPooling2D)       (None, 56, 56, 128)   0           block2_conv2[0][0]               
                                                                   block2_conv2[1][0]               
                                                                   block2_conv2[2][0]               
____________________________________________________________________________________________________
block3_conv1 (Convolution2D)     (None, 56, 56, 256)   295168      block2_pool[0][0]                
                                                                   block2_pool[1][0]                
                                                                   block2_pool[2][0]                
____________________________________________________________________________________________________
block3_conv2 (Convolution2D)     (None, 56, 56, 256)   590080      block3_conv1[0][0]               
                                                                   block3_conv1[1][0]               
                                                                   block3_conv1[2][0]               
____________________________________________________________________________________________________
block3_conv3 (Convolution2D)     (None, 56, 56, 256)   590080      block3_conv2[0][0]               
                                                                   block3_conv2[1][0]               
                                                                   block3_conv2[2][0]               
____________________________________________________________________________________________________
block3_pool (MaxPooling2D)       (None, 28, 28, 256)   0           block3_conv3[0][0]               
                                                                   block3_conv3[1][0]               
                                                                   block3_conv3[2][0]               
____________________________________________________________________________________________________
block4_conv1 (Convolution2D)     (None, 28, 28, 512)   1180160     block3_pool[0][0]                
                                                                   block3_pool[1][0]                
                                                                   block3_pool[2][0]                
____________________________________________________________________________________________________
block4_conv2 (Convolution2D)     (None, 28, 28, 512)   2359808     block4_conv1[0][0]               
                                                                   block4_conv1[1][0]               
                                                                   block4_conv1[2][0]               
____________________________________________________________________________________________________
block4_conv3 (Convolution2D)     (None, 28, 28, 512)   2359808     block4_conv2[0][0]               
                                                                   block4_conv2[1][0]               
                                                                   block4_conv2[2][0]               
____________________________________________________________________________________________________
block4_pool (MaxPooling2D)       (None, 14, 14, 512)   0           block4_conv3[0][0]               
                                                                   block4_conv3[1][0]               
                                                                   block4_conv3[2][0]               
____________________________________________________________________________________________________
block5_conv1 (Convolution2D)     (None, 14, 14, 512)   2359808     block4_pool[0][0]                
                                                                   block4_pool[1][0]                
                                                                   block4_pool[2][0]                
____________________________________________________________________________________________________
block5_conv2 (Convolution2D)     (None, 14, 14, 512)   2359808     block5_conv1[0][0]               
                                                                   block5_conv1[1][0]               
                                                                   block5_conv1[2][0]               
____________________________________________________________________________________________________
block5_conv3 (Convolution2D)     (None, 14, 14, 512)   2359808     block5_conv2[0][0]               
                                                                   block5_conv2[1][0]               
                                                                   block5_conv2[2][0]               
____________________________________________________________________________________________________
block5_pool (MaxPooling2D)       (None, 7, 7, 512)     0           block5_conv3[0][0]               
                                                                   block5_conv3[1][0]               
                                                                   block5_conv3[2][0]               
____________________________________________________________________________________________________
flatten (Flatten)                (None, 25088)         0           block5_pool[0][0]                
                                                                   block5_pool[1][0]                
                                                                   block5_pool[2][0]                
____________________________________________________________________________________________________
fc1 (Dense)                      (None, 4096)          102764544   flatten[0][0]                    
                                                                   flatten[1][0]                    
                                                                   flatten[2][0]                    
____________________________________________________________________________________________________
fc2 (Dense)                      (None, 4096)          16781312    fc1[0][0]                        
                                                                   fc1[1][0]                        
                                                                   fc1[2][0]                        
____________________________________________________________________________________________________
predictions (Dense)              (None, 1000)          4097000     fc2[0][0]                        
                                                                   fc2[1][0]                        
                                                                   fc2[2][0]                        
====================================================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
_

这与原始功能模型不同，因为新层与前一层连接了 3 次。人们说使用函数模型更强大。但我想做的只是弹出最终的预测层。而功能模型无法做到这一点……

【问题讨论】：

为什么需要顺序模型？

标签： deep-learning keras

【解决方案1】：

您可以通过定义另一个Model 将前一层作为输出来“弹出”最后一层：

poppedModel = Model(VGG_model.input,VGG_model.layers[-2].output)

此模型将共享与原始模型完全相同的权重，并且训练将影响这两个模型。

你可以在poppedModel之后添加自己的层（甚至模型），没问题：

popOut = poppedModel(input_tensor)
newLayOut = SomeKerasLayer(blablabla)(popOut)

anotherModel = Model(input_tensor, newLayOut)
#anotherModel will also share weights with poppedModel and VGG_model in the layers they have in common.

不过，重要的是，如果您打算在不影响 VGG 权重的情况下在 anotherModel 中训练新层，则在编译 anotherModel 之前将 poppedModel.trainable = False 和其中的每一层都使用 poppedModel.layers[i].trainable = False。

【讨论】：

【解决方案2】：

我也一直在为此苦苦挣扎，之前的海报几乎就在那里，但遗漏了一个以前让我难过的特定细节。确实，即使使用功能 API 创建的模型，您也可以“弹出”，但需要做更多的工作。

这是我的模型（只是普通的 VGG16）

model.summary()

____________________________________________________________________________________________________ 层（类型）输出形状参数#连接到 ==================================================== ==================================================== input_6 (InputLayer) (无, 224, 224, 3) 0 ____________________________________________________________________________________________________ block1_conv1 (Convolution2D) (None, 224, 224, 64) 1792 input_6[0][0] ____________________________________________________________________________________________________ block1_conv2 (Convolution2D) (None, 224, 224, 64) 36928 block1_conv1[0][0] ____________________________________________________________________________________________________ block1_pool (MaxPooling2D) (无, 112, 112, 64) 0 block1_conv2[0][0] ____________________________________________________________________________________________________ block2_conv1 (Convolution2D) (None, 112, 112, 128) 73856 block1_pool[0][0] ____________________________________________________________________________________________________ block2_conv2 (Convolution2D) (None, 112, 112, 128) 147584 block2_conv1[0][0] ____________________________________________________________________________________________________ block2_pool (MaxPooling2D) (无, 56, 56, 128) 0 block2_conv2[0][0] ____________________________________________________________________________________________________ block3_conv1 (Convolution2D) (None, 56, 56, 256) 295168 block2_pool[0][0] ____________________________________________________________________________________________________ block3_conv2 (Convolution2D) (无, 56, 56, 256) 590080 block3_conv1[0][0] ____________________________________________________________________________________________________ block3_conv3 (Convolution2D) (无, 56, 56, 256) 590080 block3_conv2[0][0] ____________________________________________________________________________________________________ block3_pool (MaxPooling2D) (无, 28, 28, 256) 0 block3_conv3[0][0] ____________________________________________________________________________________________________ block4_conv1 (Convolution2D) (None, 28, 28, 512) 1180160 block3_pool[0][0] ____________________________________________________________________________________________________ block4_conv2 (Convolution2D) (None, 28, 28, 512) 2359808 block4_conv1[0][0] ____________________________________________________________________________________________________ block4_conv3 (Convolution2D) (None, 28, 28, 512) 2359808 block4_conv2[0][0] ____________________________________________________________________________________________________ block4_pool (MaxPooling2D) (无, 14, 14, 512) 0 block4_conv3[0][0] ____________________________________________________________________________________________________ block5_conv1 (Convolution2D) (None, 14, 14, 512) 2359808 block4_pool[0][0] ____________________________________________________________________________________________________ block5_conv2 (Convolution2D) (None, 14, 14, 512) 2359808 block5_conv1[0][0] ____________________________________________________________________________________________________ block5_conv3 (Convolution2D) (None, 14, 14, 512) 2359808 block5_conv2[0][0] ____________________________________________________________________________________________________ block5_pool (MaxPooling2D) (无, 7, 7, 512) 0 block5_conv3[0][0] ____________________________________________________________________________________________________ 展平（展平）（无，25088）0 block5_pool[0][0] ____________________________________________________________________________________________________ fc1（密集）（无，4096）102764544 flatten[0][0] ____________________________________________________________________________________________________ fc2（密集）（无，4096）16781312 fc1[0][0] ____________________________________________________________________________________________________ 预测（密集）（无，1000）4097000 fc2[0][0] ==================================================== ==================================================== 总参数：138,357,544 可训练参数：138,357,544 不可训练参数：0 ____________________________________________________________________________________________________

然后我“弹出”了最后一层，但不使用 pop，仅使用函数式 API

#Get the last but one layer/tensor from the old model
last_layer = model.layers[-2].output

#Define the new layer/tensor for the new model
new_model = Dense(2, activation='softmax', name='Binary_predictions')(last_layer)

#Create the new model, with the old models input and the new_model tensor as the output
new_model = Model(model.input, new_model, name='Finetuned_VGG16')

#Set all layers,except the last one to not trainable
for layer in new_model.layers[:-1]: layer.trainable=False

#Compile the new model
new_model.compile(optimizer=Adam(lr=learning_rate),
              loss='categorical_crossentropy', metrics=['accuracy'])

#now train with the new outputs (cats and dogs!)

这将创建一个新模型 (new_model)，替换最后一层并修复旧层（使其不可训练）..

new_model.summary()

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_6 (InputLayer)             (None, 224, 224, 3)   0                                            
____________________________________________________________________________________________________
block1_conv1 (Convolution2D)     (None, 224, 224, 64)  1792        input_6[0][0]                    
____________________________________________________________________________________________________
block1_conv2 (Convolution2D)     (None, 224, 224, 64)  36928       block1_conv1[0][0]               
____________________________________________________________________________________________________
block1_pool (MaxPooling2D)       (None, 112, 112, 64)  0           block1_conv2[0][0]               
____________________________________________________________________________________________________
block2_conv1 (Convolution2D)     (None, 112, 112, 128) 73856       block1_pool[0][0]                
____________________________________________________________________________________________________
block2_conv2 (Convolution2D)     (None, 112, 112, 128) 147584      block2_conv1[0][0]               
____________________________________________________________________________________________________
block2_pool (MaxPooling2D)       (None, 56, 56, 128)   0           block2_conv2[0][0]               
____________________________________________________________________________________________________
block3_conv1 (Convolution2D)     (None, 56, 56, 256)   295168      block2_pool[0][0]                
____________________________________________________________________________________________________
block3_conv2 (Convolution2D)     (None, 56, 56, 256)   590080      block3_conv1[0][0]               
____________________________________________________________________________________________________
block3_conv3 (Convolution2D)     (None, 56, 56, 256)   590080      block3_conv2[0][0]               
____________________________________________________________________________________________________
block3_pool (MaxPooling2D)       (None, 28, 28, 256)   0           block3_conv3[0][0]               
____________________________________________________________________________________________________
block4_conv1 (Convolution2D)     (None, 28, 28, 512)   1180160     block3_pool[0][0]                
____________________________________________________________________________________________________
block4_conv2 (Convolution2D)     (None, 28, 28, 512)   2359808     block4_conv1[0][0]               
____________________________________________________________________________________________________
block4_conv3 (Convolution2D)     (None, 28, 28, 512)   2359808     block4_conv2[0][0]               
____________________________________________________________________________________________________
block4_pool (MaxPooling2D)       (None, 14, 14, 512)   0           block4_conv3[0][0]               
____________________________________________________________________________________________________
block5_conv1 (Convolution2D)     (None, 14, 14, 512)   2359808     block4_pool[0][0]                
____________________________________________________________________________________________________
block5_conv2 (Convolution2D)     (None, 14, 14, 512)   2359808     block5_conv1[0][0]               
____________________________________________________________________________________________________
block5_conv3 (Convolution2D)     (None, 14, 14, 512)   2359808     block5_conv2[0][0]               
____________________________________________________________________________________________________
block5_pool (MaxPooling2D)       (None, 7, 7, 512)     0           block5_conv3[0][0]               
____________________________________________________________________________________________________
flatten (Flatten)                (None, 25088)         0           block5_pool[0][0]                
____________________________________________________________________________________________________
fc1 (Dense)                      (None, 4096)          102764544   flatten[0][0]                    
____________________________________________________________________________________________________
fc2 (Dense)                      (None, 4096)          16781312    fc1[0][0]                        
____________________________________________________________________________________________________
Binary_predictions (Dense)       (None, 2)             8194        fc2[0][0]                        
====================================================================================================
Total params: 134,268,738
Trainable params: 8,194
Non-trainable params: 134,260,544

棘手的部分是将 .output 作为最后一层，因为这使它成为一个张量。然后使用该张量作为新 Dense 层的输入，并将其作为新模型中的最终输出...

希望对您有所帮助...

顿

【讨论】：