VGG16模型-tensorflow实现的架构

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import InputLayer, Dense, Flatten, Conv2D, MaxPooling2D
from tensorflow.keras.optimizers import Adam

def build_vgg16(input_shape, num_classes):
    model = Sequential()
    model.add(InputLayer(input_shape=input_shape))
    
    # 卷积层 1
    model.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
    
    # 卷积层 2
    model.add(Conv2D(filters=128, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=128, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
    
    # 卷积层 3
    model.add(Conv2D(filters=256, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=256, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=256, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
    
    # 卷积层 4
    model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
    
    # 卷积层 5
    model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(Conv2D(filters=512, kernel_size=(3,3), padding='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
    
    # 分类
    model.add(Flatten())
    model.add(Dense(units=4096, activation='relu'))
    model.add(Dense(units=4096, activation='relu'))
    model.add(Dense(units=num_classes, activation='softmax'))
    
    # 编译模型
    model.compile(optimizer=Adam(learning_rate=0.001),
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])
    return model