一.VGG概述

VGGNet是牛津大学视觉几何组(Visual Geometry Group)提出的模型，该模型在2014ImageNet图像分类与定位挑战赛 ILSVRC-2014中取得在分类任务第二，定位任务第一的优异成绩。VGGNet突出的贡献是证明了很小的卷积，通过增加网络深度可以有效提高性能。VGG很好的继承了Alexnet的衣钵同时拥有着鲜明的特点。即网络层次较深。

VGGNet结构

VGGNet模型有A-E五种结构网络，深度分别为11,11,13,16,19。其中较为典型的网络结构主要有vgg16和vgg19，本篇文章主要讲VGG16,并分享VGG16的Keras实现。其网络结构如下图中D列（红色方框）：

VGG16网络结构

vggnet对输入图像的默认大小是224*224*3 （从表中input可以看出）。vgg16网络结构含有参数的网络层一共有16层，即13个卷积层，5个池化层，3个全连接层，不包括激活层。

vgg16网络结构可以划分为6个模块层次加1个输入模块，分别如下

模块	各模块的涉及的层次
输入模块	*2242243*
第一个模块	conv3-64
	conv3-64
	maxpool
第二个模块	conv3-128
	conv3-128
	maxpool
第三个模块	conv3-256
	conv3-256
	conv3-256
	maxpool
第四个模块	conv3-512
	conv3-512
	conv3-512
	maxpool
第五个模块	conv-512
	conv3-512
	conv3-512
	maxpool
第六个模块（全连接层和输出层）	FC-4096 （实际上前面需要加一个Flatten层）
	FC-4096
	FC-1000 (负责分类)
	softmax(输出层函数)

二.vgg16实现MNIST分类

（基于keras框架）

代码实现：

#从keras.model中导入model模块，为函数api搭建网络做准备
from keras.models import Model
from keras.layers import Flatten,Dense,Dropout,MaxPooling2D,Conv2D,BatchNormalization,Input,ZeroPadding2D,Concatenate
from keras.layers.convolutional import AveragePooling2D
from keras import regularizers  #正则化
from keras.optimizers import RMSprop  #优化选择器
from keras.layers import AveragePooling2D
from keras.datasets import mnist
from keras.utils import np_utils
import matplotlib.pyplot as plt
import numpy as np#数据处理
(X_train,Y_train),(X_test,Y_test)=mnist.load_data()
X_test1=X_test
Y_test1=Y_test
X_train=X_train.reshape(-1,28,28,1).astype("float32")/255.0
X_test=X_test.reshape(-1,28,28,1).astype("float32")/255.0
Y_train=np_utils.to_categorical(Y_train,10)
Y_test=np_utils.to_categorical(Y_test,10)
print(X_train.shape)
print(Y_train.shape)
print(X_train.shape)def vgg16():x_input = Input((28, 28, 1))  # 输入数据形状28*28*1# Block 1x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(x_input)x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)# Block 2x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)# Block 3x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)# Block 4x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)# Block 5x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)#BLOCK 6x=Flatten()(x)x=Dense(256,activation="relu")(x)x=Dropout(0.5)(x)x = Dense(256, activation="relu")(x)x = Dropout(0.5)(x)#搭建最后一层，即输出层x = Dense(10, activation="softmax")(x)# 调用MDOEL函数，定义该网络模型的输入层为X_input,输出层为x.即全连接层model = Model(inputs=x_input, outputs=x)# 查看网络模型的摘要model.summary()return model
model=vgg16()
optimizer=RMSprop(lr=1e-4)
model.compile(loss="binary_crossentropy",optimizer=optimizer,metrics=["accuracy"])
#训练加评估模型
n_epoch=4
batch_size=128
def run_model(): #训练模型training=model.fit(X_train,Y_train,batch_size=batch_size,epochs=n_epoch,validation_split=0.25,verbose=1)test=model.evaluate(X_train,Y_train,verbose=1)return training,test
training,test=run_model()
print("误差：",test[0])
print("准确率：",test[1])def show_train(training_history,train, validation):plt.plot(training.history[train],linestyle="-",color="b")plt.plot(training.history[validation] ,linestyle="--",color="r")plt.title("training history")plt.xlabel("epoch")plt.ylabel("accuracy")plt.legend(["training","validation"],loc="lower right")plt.show()
show_train(training,"accuracy","val_accuracy")def show_train1(training_history,train, validation):plt.plot(training.history[train],linestyle="-",color="b")plt.plot(training.history[validation] ,linestyle="--",color="r")plt.title("training history")plt.xlabel("epoch")plt.ylabel("loss")plt.legend(["training","validation"],loc="upper right")plt.show()
show_train1(training,"loss","val_loss")prediction=model.predict(X_test)
def image_show(image):fig=plt.gcf()  #获取当前图像fig.set_size_inches(2,2)  #改变图像大小plt.imshow(image,cmap="binary")  #显示图像plt.show()
def result(i):image_show(X_test1[i])print("真实值：",Y_test1[i])print("预测值：",np.argmax(prediction[i]))
result(0)
result(1)