Добавляйте отбрасывающие слои между предварительно обработанными плотными слоями в керасе

В keras.applications есть модель VGG16, предварительно обученная на imagenet.

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

Эта модель имеет следующую структуру.


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
____________________________________________________________________________________________________

Я хотел бы настроить эту модель с отсеивающими слоями между плотными слоями (fc1, fc2 и предсказаниями), сохраняя при этом все предварительно подготовленные веса модели неповрежденными. Я знаю, что можно получить доступ к каждому слою отдельно с помощью model.layers, но я не нашел нигде, как добавлять новые слои между существующими уровнями.

Какая лучшая практика?

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)

____________________________________________________________________________________________________ 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 ____________________________________________________________________________________________________

Ответ 1