在 keras 中預訓練的密集層之間添加 dropout 層

Question

在keras.applications ，有一個在 imagenet 上預訓練的 VGG16 模型。

from keras.applications import VGG16
model = VGG16(weights='imagenet')

該模型具有以下結構。

Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_1 (InputLayer)             (None, 3, 224, 224)   0                                            
____________________________________________________________________________________________________
block1_conv1 (Convolution2D)     (None, 64, 224, 224)  1792        input_1[0][0]                    
____________________________________________________________________________________________________
block1_conv2 (Convolution2D)     (None, 64, 224, 224)  36928       block1_conv1[0][0]               
____________________________________________________________________________________________________
block1_pool (MaxPooling2D)       (None, 64, 112, 112)  0           block1_conv2[0][0]               
____________________________________________________________________________________________________
block2_conv1 (Convolution2D)     (None, 128, 112, 112) 73856       block1_pool[0][0]                
____________________________________________________________________________________________________
block2_conv2 (Convolution2D)     (None, 128, 112, 112) 147584      block2_conv1[0][0]               
____________________________________________________________________________________________________
block2_pool (MaxPooling2D)       (None, 128, 56, 56)   0           block2_conv2[0][0]               
____________________________________________________________________________________________________
block3_conv1 (Convolution2D)     (None, 256, 56, 56)   295168      block2_pool[0][0]                
____________________________________________________________________________________________________
block3_conv2 (Convolution2D)     (None, 256, 56, 56)   590080      block3_conv1[0][0]               
____________________________________________________________________________________________________
block3_conv3 (Convolution2D)     (None, 256, 56, 56)   590080      block3_conv2[0][0]               
____________________________________________________________________________________________________
block3_pool (MaxPooling2D)       (None, 256, 28, 28)   0           block3_conv3[0][0]               
____________________________________________________________________________________________________
block4_conv1 (Convolution2D)     (None, 512, 28, 28)   1180160     block3_pool[0][0]                
____________________________________________________________________________________________________
block4_conv2 (Convolution2D)     (None, 512, 28, 28)   2359808     block4_conv1[0][0]               
____________________________________________________________________________________________________
block4_conv3 (Convolution2D)     (None, 512, 28, 28)   2359808     block4_conv2[0][0]               
____________________________________________________________________________________________________
block4_pool (MaxPooling2D)       (None, 512, 14, 14)   0           block4_conv3[0][0]               
____________________________________________________________________________________________________
block5_conv1 (Convolution2D)     (None, 512, 14, 14)   2359808     block4_pool[0][0]                
____________________________________________________________________________________________________
block5_conv2 (Convolution2D)     (None, 512, 14, 14)   2359808     block5_conv1[0][0]               
____________________________________________________________________________________________________
block5_conv3 (Convolution2D)     (None, 512, 14, 14)   2359808     block5_conv2[0][0]               
____________________________________________________________________________________________________
block5_pool (MaxPooling2D)       (None, 512, 7, 7)     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
____________________________________________________________________________________________________

我想用密集層（fc1、fc2 和預測）之間的 dropout 層微調這個模型，同時保持模型的所有預訓練權重完好無損。 我知道可以使用model.layers單獨訪問每個圖層，但我還沒有找到如何在現有圖層之間添加新圖層的任何地方。

這樣做的最佳做法是什么？

Answer 1

我自己通過使用Keras 函數式 API找到了答案

from keras.applications import VGG16
from keras.layers import Dropout
from keras.models import Model

model = VGG16(weights='imagenet')

# Store the fully connected layers
fc1 = model.layers[-3]
fc2 = model.layers[-2]
predictions = model.layers[-1]

# Create the dropout layers
dropout1 = Dropout(0.85)
dropout2 = Dropout(0.85)

# Reconnect the layers
x = dropout1(fc1.output)
x = fc2(x)
x = dropout2(x)
predictors = predictions(x)

# Create a new model
model2 = Model(input=model.input, output=predictors)

model2有我想要的model2層

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_1 (InputLayer)             (None, 3, 224, 224)   0                                            
____________________________________________________________________________________________________
block1_conv1 (Convolution2D)     (None, 64, 224, 224)  1792        input_1[0][0]                    
____________________________________________________________________________________________________
block1_conv2 (Convolution2D)     (None, 64, 224, 224)  36928       block1_conv1[0][0]               
____________________________________________________________________________________________________
block1_pool (MaxPooling2D)       (None, 64, 112, 112)  0           block1_conv2[0][0]               
____________________________________________________________________________________________________
block2_conv1 (Convolution2D)     (None, 128, 112, 112) 73856       block1_pool[0][0]                
____________________________________________________________________________________________________
block2_conv2 (Convolution2D)     (None, 128, 112, 112) 147584      block2_conv1[0][0]               
____________________________________________________________________________________________________
block2_pool (MaxPooling2D)       (None, 128, 56, 56)   0           block2_conv2[0][0]               
____________________________________________________________________________________________________
block3_conv1 (Convolution2D)     (None, 256, 56, 56)   295168      block2_pool[0][0]                
____________________________________________________________________________________________________
block3_conv2 (Convolution2D)     (None, 256, 56, 56)   590080      block3_conv1[0][0]               
____________________________________________________________________________________________________
block3_conv3 (Convolution2D)     (None, 256, 56, 56)   590080      block3_conv2[0][0]               
____________________________________________________________________________________________________
block3_pool (MaxPooling2D)       (None, 256, 28, 28)   0           block3_conv3[0][0]               
____________________________________________________________________________________________________
block4_conv1 (Convolution2D)     (None, 512, 28, 28)   1180160     block3_pool[0][0]                
____________________________________________________________________________________________________
block4_conv2 (Convolution2D)     (None, 512, 28, 28)   2359808     block4_conv1[0][0]               
____________________________________________________________________________________________________
block4_conv3 (Convolution2D)     (None, 512, 28, 28)   2359808     block4_conv2[0][0]               
____________________________________________________________________________________________________
block4_pool (MaxPooling2D)       (None, 512, 14, 14)   0           block4_conv3[0][0]               
____________________________________________________________________________________________________
block5_conv1 (Convolution2D)     (None, 512, 14, 14)   2359808     block4_pool[0][0]                
____________________________________________________________________________________________________
block5_conv2 (Convolution2D)     (None, 512, 14, 14)   2359808     block5_conv1[0][0]               
____________________________________________________________________________________________________
block5_conv3 (Convolution2D)     (None, 512, 14, 14)   2359808     block5_conv2[0][0]               
____________________________________________________________________________________________________
block5_pool (MaxPooling2D)       (None, 512, 7, 7)     0           block5_conv3[0][0]               
____________________________________________________________________________________________________
flatten (Flatten)                (None, 25088)         0           block5_pool[0][0]                
____________________________________________________________________________________________________
fc1 (Dense)                      (None, 4096)          102764544   flatten[0][0]                    
____________________________________________________________________________________________________
dropout_1 (Dropout)              (None, 4096)          0           fc1[0][0]                        
____________________________________________________________________________________________________
fc2 (Dense)                      (None, 4096)          16781312    dropout_1[0][0]                  
____________________________________________________________________________________________________
dropout_2 (Dropout)              (None, 4096)          0           fc2[1][0]                        
____________________________________________________________________________________________________
predictions (Dense)              (None, 1000)          4097000     dropout_2[0][0]                  
====================================================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
____________________________________________________________________________________________________

Answer 2

這是一個保留在 Keras“Sequential API”中的解決方案。

您可以遍歷這些層並將它們按順序添加到更新的 Sequential 模型中。 使用 if 子句在您選擇的層之后添加 Dropouts。

from tensorflow.keras.applications import VGG16
from tensorflow.keras.layers import Dropout
from tensorflow.keras.models import Sequential

model = VGG16(weights='imagenet')

# check structure and layer names before looping
model.summary()

# loop through layers, add Dropout after layers 'fc1' and 'fc2'
updated_model = Sequential()
for layer in model.layers:
    updated_model.add(layer)
    if layer.name in ['fc1', 'fc2']:
        updated_model.add(Dropout(.2))

model = updated_model

# check structure
model.summary()