函数式模型

一、搭建单通道模型

搭建单通道模型，使用序贯（Sequential）模型和函数式（Functional）模型搭建都可以。

1.序贯（Sequential）模型搭建

搭建代码：

# 定义序贯模型
model = Sequential()

# 第一个卷积层
# input_shape 输入平面
# filters 卷积核/滤波器个数
# kernel_size 卷积窗口大小
# strides 步长
# padding padding方式 same/valid
# activation 激活函数
model.add(Conv2D(
    input_shape = (28,28,1),
    filters = 32,
    kernel_size = 5,
    strides = 1,
    padding = 'same',
    activation = 'relu'
))
# 第一个池化层
model.add(MaxPooling2D(
    pool_size = 2,
    strides = 2,
    padding = 'same',
))
# 第二个卷积层
model.add(Conv2D(64,5,strides=1,padding='same',activation = 'relu'))
# 第二个池化层
model.add(MaxPooling2D(2,2,'same'))
# 把第二个池化层的输出扁平化为1维
model.add(Flatten())
# 第一个全连接层
model.add(Dense(1024,activation = 'relu'))
# Dropout
model.add(Dropout(0.5))
# 第二个全连接层
model.add(Dense(10,activation='softmax'))

2.函数式（Functional）模型搭建

搭建代码：

inputs = Input(shape=(28,28,1))
x = Conv2D(filters=32, kernel_size=5, padding='same', activation='relu')(inputs)
x = MaxPooling2D(pool_size = 2)(x)
x = Conv2D(filters=64, kernel_size=5, padding='same', activation='relu')(x)
x = MaxPooling2D(pool_size = 2)(x)
x = Flatten()(x)
x = Dense(1024,activation = 'relu')(x)
x = Dropout(0.5)(x)
predictions = Dense(10,activation='softmax')(x)
model = Model(inputs=inputs, outputs=predictions)

使用时需要导入from keras.models import Model。

二、搭建多通道模型

除了常见的单通道模型之外，还有着许多知名的多通道模型。例如google的Inception:

就是典型的多通道模型。序贯（Sequential）模型只能定义有一个通道的模型，假如一个模型有很多通道的话，那么Sequential()序贯模型就定义不了，这个时候就只能使用函数式模型进行网络模型搭建。
搭建部分多通道Inception网络模型代码：

from keras.layers import Conv2D, MaxPooling2D, Input

input_img = Input(shape=(256, 256, 3))

tower_1 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_1 = Conv2D(64, (3, 3), padding='same', activation='relu')(tower_1)

tower_2 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_2 = Conv2D(64, (5, 5), padding='same', activation='relu')(tower_2)

tower_3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(input_img)
tower_3 = Conv2D(64, (1, 1), padding='same', activation='relu')(tower_3)

output = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)

三、完整代码

代码运行平台为jupyter-notebook，文章中的代码块，也是按照jupyter-notebook中的划分顺序进行书写的，运行文章代码，直接分单元粘入到jupyter-notebook即可。

1.导入第三方库

import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense,Dropout,Conv2D,MaxPooling2D,Flatten,Input
from keras.optimizers import Adam
from keras.models import Model

2.数据处理

# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
# (60000,28,28)->(60000,28,28,1)
x_train = x_train.reshape(-1,28,28,1)/255.0
x_test = x_test.reshape(-1,28,28,1)/255.0
# 换one hot格式
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)

3.序贯（Sequential）模型搭建单通道网络

# 定义序贯模型
model = Sequential()

# 第一个卷积层
# input_shape 输入平面
# filters 卷积核/滤波器个数
# kernel_size 卷积窗口大小
# strides 步长
# padding padding方式 same/valid
# activation 激活函数
model.add(Conv2D(
    input_shape = (28,28,1),
    filters = 32,
    kernel_size = 5,
    strides = 1,
    padding = 'same',
    activation = 'relu'
))
# 第一个池化层
model.add(MaxPooling2D(
    pool_size = 2,
    strides = 2,
    padding = 'same',
))
# 第二个卷积层
model.add(Conv2D(64,5,strides=1,padding='same',activation = 'relu'))
# 第二个池化层
model.add(MaxPooling2D(2,2,'same'))
# 把第二个池化层的输出扁平化为1维
model.add(Flatten())
# 第一个全连接层
model.add(Dense(1024,activation = 'relu'))
# Dropout
model.add(Dropout(0.5))
# 第二个全连接层
model.add(Dense(10,activation='softmax'))

4.函数式（Functional）模型搭建单通道网络

inputs = Input(shape=(28,28,1))
x = Conv2D(filters=32, kernel_size=5, padding='same', activation='relu')(inputs)
x = MaxPooling2D(pool_size = 2)(x)
x = Conv2D(filters=64, kernel_size=5, padding='same', activation='relu')(x)
x = MaxPooling2D(pool_size = 2)(x)
x = Flatten()(x)
x = Dense(1024,activation = 'relu')(x)
x = Dropout(0.5)(x)
predictions = Dense(10,activation='softmax')(x)
model = Model(inputs=inputs, outputs=predictions)

5.训练模型

# 定义优化器
adam = Adam(lr=1e-4)

# 定义优化器，loss function，训练过程中计算准确率
model.compile(optimizer=adam,loss='categorical_crossentropy',metrics=['accuracy'])

# 训练模型
model.fit(x_train,y_train,batch_size=64,epochs=10)

# 评估模型
loss,accuracy = model.evaluate(x_test,y_test)

print('test loss',loss)
print('test accuracy',accuracy)

6.函数式模型搭建多通道网络

from keras.layers import Conv2D, MaxPooling2D, Input

input_img = Input(shape=(256, 256, 3))

tower_1 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_1 = Conv2D(64, (3, 3), padding='same', activation='relu')(tower_1)

tower_2 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_2 = Conv2D(64, (5, 5), padding='same', activation='relu')(tower_2)

tower_3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(input_img)
tower_3 = Conv2D(64, (1, 1), padding='same', activation='relu')(tower_3)

output = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)