您是否应该为特定任务重新训练VGG16?绝对不!重新训练如此庞大的网络很难,并且需要很多直觉和知识来培训深层网络.让我们分析为什么你可以使用在ImageNet上预训练的权重来完成你的任务:
> ImageNet是一个庞大的数据集,包含数百万个图像. VGG16本身已在3-4天左右的强大GPU上接受过培训.在CPU上(假设您没有像NVIDIA GeForce Titan X那样强大的GPU)需要数周时间.
> ImageNet包含来自现实世界场景的图像. NBA比赛也可以被视为现实世界的场景.因此,ImageNet功能的预训练很可能也可用于NBA比赛.
实际上,您不需要使用预先训练过的VGG16的所有卷积层.让我们看看visualization of internal VGG16 layers并看看它们检测到了什么(取自this article;图像太大,所以我只提供了一个紧凑的链接):
>第一个和第二个卷积块查看低级特征,例如角,边等.
>第三和第四个卷积块查看曲面特征,曲线,圆等.
>第五层着眼于高级功能
因此,您可以决定哪种功能对您的特定任务有益.在第5街区你需要高水平的功能吗?或者您可能想要使用第3块的中级功能?也许你想在VGG底层叠加另一个神经网络?有关更多说明,请查看我编写的以下教程;它曾经是SO文档.
使用VGG和Keras进行传输学习和微调
在这个例子中,提出了三个简短而全面的子示例:
>从Keras库附带的可用预训练模型中加载重量
>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
Keras提供包括VGG-16和VGG-19在内的ImageNet模型的预训练.在此示例中,此处和之后将使用VGG-16.欲了解更多信息,请访问Keras Applications documentation.
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
假设对于具有大小(160,160,3)的图像的某些特定任务,您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
假设您需要通过将block1_conv1和block2_conv2替换为单个卷积层来加速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,然后再组装.以下是专门针对您的任务的代码:
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)