深度学习笔记--使用keras创建和加载VGG模型

VGG16模型，顾名思义，有16层，通过学习github上的源码，发现其中有13层为卷积层（conv），3层为全连接（Dense），还有若干层pooling层。
使用keras建立一个模型的instance有两种方式，一个是通过Input类构建，一个则是通过model类构建，具体的形式有所不同，本文采用Input类构建，这里默认输入图片大小为（50，50，3）。使用代码可以清晰看出VGG的每一层参数。

这里加载模型的参数，需要下载h5文件到本地，这里主要介绍建立VGG16模型的步骤，代码主要参照keras VGG源码，地址：

https://github.com/tensorflow/tensorflow/blob/r1.10/tensorflow/python/keras/applications/vgg16.py

import tensorflow as tf
from tensorflow import keras
from keras import Model,Sequential
from keras.layers import Flatten, Dense, Conv2D, GlobalAveragePooling2D
from keras.layers import Input, MaxPooling2D, GlobalMaxPooling2D


def VGG16(num_classes,importModel = None):

    image_input = Input(shape = (50,50,3))
    #block1
    x = Conv2D(64,(3,3),activation = 'relu',padding = 'same',name = 'block1_conv1')(image_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)
    #block2
    x = 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)
    #block3
    x = 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((