Vgg16神经网络简介与代码实战

1.介绍

vgg被发表在ICLR 2015上，论文作者是Goolge DeepMind，这系列model在ILSVRC-2013达到了best-performance，并且在其他以DCNN为基础的工作达到了很好的效果（例如FCN）

2.模型结构

 

3.模型特点
比起Alexnet，Vgg对图片有更精确的估值以及更省空间

与Alexnet对比：

相同点：

1.最后三层FC层（Fully Connected全连接层）结构相同。

2.都分成五层（组）。

3.每层和每层之间用pooling层分开

不同点：

1.作者在论文中说了一句"This can be seen as imposing a regularisation on the 7 × 7 conv. filters, forcing them to have a decomposition through the 3 × 3 filters"他说7x7 filter可以被分解成若干个3x3的filter的叠加，VGG每层含有多个（2~4）个 Convolution层，filter的大小3X3(最小)。很明显，VGG是在模仿Alex的结构，然而它通过降低filter的大小，增加层数来达到同样的结果。

2.AlexNet的Channel明显小于VGG。猜想VGG之所以能达到更高的精准性，源自于更多的Channel数，而由于filter size的减少，channel可以大幅度增加，更多的信息可以被提取。

4.代码实现keras

from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
 
model = Sequential()
model.add(Conv2D(64, (3, 3), strides=(1, 1), input_shape=(224, 224, 3), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(64, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2, 2)))
 
model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2, 2)))
 
model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2, 2)))
 
model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2, 2)))
 
model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2, 2)))
 
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
model.summary()