使用 Keras 和 VGG 进行转学习

在这个例子中,提出了三个简短而全面的子示例:

  • Keras 库附带的可用预训练模型加载重量
  • 在 VGG 的任何层之上堆叠另一个网络进行培训
  • 在其他图层的中间插入图层
  • 使用 VGG 进行微调和转移学习的提示和一般经验法则

加载预先训练的重量

预先训练上 ImageNet 车型,其中包括 VGG-16VGG-19 中,都可以 Keras 。在此示例中,将使用 VGG-16 。有关更多信息,请访问 Keras Applications 文档

from keras import applications

# This will load the whole VGG16 network, including the top Dense layers.
# Note: by specifying the shape of top layers, input tensor shape is forced
# to be (224, 224, 3), therefore you can use it only on 224x224 images.
vgg_model = applications.VGG16(weights='imagenet', include_top=True)

# If you are only interested in convolution filters. Note that by not
# specifying the shape of top layers, the input tensor shape is (None, None, 3),
# so you can use them for any size of images.
vgg_model = applications.VGG16(weights='imagenet', include_top=False)

# If you want to specify input tensor
from keras.layers import Input
input_tensor = Input(shape=(160, 160, 3))
vgg_model = applications.VGG16(weights='imagenet',
                               include_top=False,
                               input_tensor=input_tensor)

# To see the models' architecture and layer names, run the following
vgg_model.summary()

使用从 VGG 获取的底层创建新网络

假设对于尺寸为 (160, 160, 3) 的图像的某些特定任务,你希望使用预先训练的 VGG 底层,最多使用名称 block2_pool 的图层。

vgg_model = applications.VGG16(weights='imagenet',
                               include_top=False,
                               input_shape=(160, 160, 3))

# Creating dictionary that maps layer names to the layers
layer_dict = dict([(layer.name, layer) for layer in vgg_model.layers])

# Getting output tensor of the last VGG layer that we want to include
x = layer_dict['block2_pool'].output

# Stacking a new simple convolutional network on top of it    
x = Conv2D(filters=64, kernel_size=(3, 3), activation='relu')(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = Flatten()(x)
x = Dense(256, activation='relu')(x)
x = Dropout(0.5)(x)
x = Dense(10, activation='softmax')(x)

# Creating new model. Please note that this is NOT a Sequential() model.
from keras.models import Model
custom_model = Model(input=vgg_model.input, output=x)

# Make sure that the pre-trained bottom layers are not trainable
for layer in custom_model.layers[:7]:
    layer.trainable = False

# Do not forget to compile it
custom_model.compile(loss='categorical_crossentropy',
                     optimizer='rmsprop',
                     metrics=['accuracy'])

删除多个图层并在中间插入一个新图层

假设你需要通过用单个卷积层替换 block1_conv1block2_conv2 来加速 VGG16,以便保存预先训练的权重。我们的想法是将整个网络拆分为单独的层,然后将其组装回来。以下是专门针对你的任务的代码:

vgg_model = applications.VGG16(include_top=True, weights='imagenet')

# Disassemble layers
layers = [l for l in vgg_model.layers]

# Defining new convolutional layer.
# Important: the number of filters should be the same!
# Note: the receiptive field of two 3x3 convolutions is 5x5.
new_conv = Conv2D(filters=64, 
                  kernel_size=(5, 5),
                  name='new_conv',
                  padding='same')(layers[0].output)

# Now stack everything back
# Note: If you are going to fine tune the model, do not forget to
#       mark other layers as un-trainable
x = new_conv
for i in range(3, len(layers)):
    layers[i].trainable = False
    x = layers[i](x)

# Final touch
result_model = Model(input=layer[0].input, output=x)