keras学习笔记（二）

学习过tensorflow后，继续学习了keras，想用keras自己去写一个卷积神经网络，用于cifar10的数据分类问题。

实例：CIFAR10分类

下面代码主要介绍了keras中三种构建网络结构的方式，仅供参考，可能还有更多的写网络结构的方式，但目前我作为初学者，了解的没有那么广泛。

'''
注：第二种构建网络方法，我没有写完，so识别精度很低，但是可以跑通，如果有兴趣的话可以自己去补全，
我没有加任何的技巧，所以另外两种方法的精度在0.75左右。如果想达到一个较高的识别率，请参考
我修改别人完全写好的用在mnist数据上的代码，我修改了数据集和网络参数，精度达到0.99。
另外，这三种构建网络的办法我均用了注释号注释掉了，自己想去实现的话，选择其中一种，将注释去掉即可
'''
import keras
import keras.layers
import numpy as np
from keras.utils import np_utils
from keras.layers import Dense,Activation,Convolution2D,MaxPooling2D,Flatten,Dropout
from keras.optimizers import RMSprop
#数据预处理
nb_classes=10
(X_train, Y_train), (X_test,Y_test) = keras.datasets.cifar10.load_data()
X_train = X_train.astype('float32')/255
X_test = X_test.astype('float32')/255
#将Y_train的shape由一列，变为一行
Y_train =Y_train.reshape(Y_train.shape[0])/10#一种非常好的标签处理方式，如果不对标签进行处理，我得到的精度只有0.75，加上这两句之后，提升到了0.99
Y_test = Y_test.reshape(Y_test.shape[0])/10
Y_train=np_utils.to_categorical(Y_train,nb_classes)#一种编码方式，one-hot编码，比如第二个类别就是第二个数是1，其他都是0
Y_test =np_utils.to_categorical(Y_test ,nb_classes)

#第一种建立神经网络模型的方法，由输入到输出。
#keras.Input开始定义输入，每一层后面都加一个小括号，把上一层的输出放进去，表示这一层的输入，对于其他的参数如果不理解，请参考之前的博客
x = keras.Input  (shape=(32, 32, 3))
#在层内参数部分设置的激活函数activation=，首字母一定小写，否则报错。
y = Convolution2D(filters  = 64, kernel_size=3, strides=1, padding='same', activation='relu')(x)
y = Convolution2D(filters  = 64, kernel_size=3, strides=1, padding='same', activation='relu')(y)
y = MaxPooling2D (pool_size= 2,  strides = 2,   padding='same')(y)
y = Convolution2D(filters  = 128,kernel_size=3, strides=1, padding='same', activation='relu')(y)
y = Convolution2D(filters  = 128,kernel_size=3, strides=1, padding='same', activation='relu')(y)
y = MaxPooling2D (pool_size=2,   strides = 2,   padding='same')(y)
y = Convolution2D(filters  = 256,kernel_size=3, strides=1, padding='same', activation='relu')(y)
y = Convolution2D(filters  = 256,kernel_size=3, strides=1, padding='same', activation='relu')(y)
y = MaxPooling2D (pool_size=2,   strides = 2,   padding='same')(y)
y = Flatten()(y)
y = Dropout(0.5)(y) #添加随机失活层，这个机制可以降低过拟合
y = Dense(units=nb_classes, activation='softmax')(y)
model = keras.models.Model(inputs=x, outputs=y, name='model')
model.summary()

'''
#第二种建立神经网络模型的方法（建立一个模型，然后不断添加隐藏层）
model=keras.Sequential()
#这里的激活函数的首字母一定不要大写，大写了就一直报错。找错找了半天
model.add(keras.layers.Conv2D(filters=64, kernel_size=3, strides=1, padding='same',activation='relu'))
model.add(keras.layers.Conv2D(filters=64, kernel_size=3, strides=1, padding='same',activation='relu'))
model.add(keras.layers.MaxPooling2D(pool_size=2, strides=2, padding='same'))
model.add(keras.layers.Conv2D(filters=128,kernel_size=3,strides=1,padding='same',activation='relu'))
model.add(keras.layers.Conv2D(filters=128,kernel_size=3,strides=1,padding='same',activation='relu'))
model.add(keras.layers.MaxPooling2D(pool_size=2, strides=2, padding='same'))
model.add(keras.layers.Conv2D(filters=256,kernel_size=3,strides=1,padding='same',activation='relu'))
model.add(keras.layers.Conv2D(filters=128,kernel_size=3,strides=1,padding='same',activation='relu'))
model.add(keras.layers.MaxPooling2D(pool_size=2, strides=2, padding='same'))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dropout(0.5))
model.add(Dense(10,activation='softmax'))
'''
'''
#第三种建立神经网络的方法（直接在Sequential中添加隐藏层）
model=keras.Sequential([
    keras.layers.Conv2D(filters=64, kernel_size=3, strides=1, padding='same', kernel_initializer='he_normal'),
    Activation('relu'),     #这种形式设置激活函数Activation首字母要大写
    keras.layers.Conv2D(filters=64, kernel_size=3, strides=1, padding='same', kernel_initializer='he_normal'),
    Activation('relu'),
    MaxPooling2D(pool_size=2, strides=2, padding='same'),
    keras.layers.Conv2D(filters=128, kernel_size=3, strides=1, padding='same', kernel_initializer='he_normal'),
    Activation('relu'),
    keras.layers.Conv2D(filters=128, kernel_size=3, strides=1, padding='same', kernel_initializer='he_normal'),
    Activation('relu'),
    MaxPooling2D(pool_size=2, strides=2, padding='same'),
    Convolution2D(filters=256, kernel_size=3, strides=1, padding='same', kernel_initializer='he_normal'),
    Activation('relu'),
    Convolution2D(filters=256, kernel_size=3, strides=1, padding='same', kernel_initializer='he_normal'),
    Activation('relu'),
    MaxPooling2D(pool_size=2, strides=2, padding='same'),
    Flatten(),
    Dropout(0.5),
    Dense(10),#注意这里的10千万不要手残打引号，这个错误我也找了半天，表示最后全连接层的输入维度为10
    Activation('softmax')#经过softmax处理后，将图片分类
])
'''
#建立模型包括网络，优化器，损失函数
optimizer=keras.optimizers.RMSprop(lr=0.001,rho=0.9,epsilon=1e-8,decay=0.0)
model.compile(loss='categorical_crossentropy',optimizer=optimizer,metrics=['accuracy'])#metrics可以存储一些训练过程中的我想要的数据
#迭代训练
model.fit(X_train,Y_train,nb_epoch=10,batch_size=100)
loss,accuracy=model.evaluate(X_test,Y_test)
print('test loss',loss)
print('accuracy',accuracy)

我自己写的这几个网络结构，训练过程如下图所示：

下面这一段是我修改别人完全写好的用在mnist数据上的代码，我修改了数据集和网络参数，精度达到0.99。

import keras.layers
import numpy as np
from keras.utils import np_utils
from keras import Sequential
from keras.layers import Dense,Activation,Convolution2D,MaxPooling2D,Flatten,Dropout
from keras.optimizers import RMSprop
from keras.models import Model

nb_classes = 10
(X_train, Y_train), (X_test, Y_test) = keras.datasets.cifar10.load_data()
Y_train =Y_train.reshape(Y_train.shape[0])/10
Y_test = Y_test.reshape(Y_test.shape[0])/10
Y_train = np_utils.to_categorical(Y_train, nb_classes)
Y_test = np_utils.to_categorical(Y_test, nb_classes)

x = keras.Input(shape=(32, 32, 3))
y = x
y = Convolution2D(filters=64, kernel_size=3, strides=1, padding='same', activation='relu', kernel_initializer='he_normal')(y)
y = Convolution2D(filters=64, kernel_size=3, strides=1, padding='same', activation='relu', kernel_initializer='he_normal')(y)
y = MaxPooling2D(pool_size=2, strides=2, padding='same')(y)
y = Convolution2D(filters=128, kernel_size=3, strides=1, padding='same', activation='relu', kernel_initializer='he_normal')(y)
y = Convolution2D(filters=128, kernel_size=3, strides=1, padding='same', activation='relu', kernel_initializer='he_normal')(y)
y = MaxPooling2D(pool_size=2, strides=2, padding='same')(y)
y = Convolution2D(filters=256, kernel_size=3, strides=1, padding='same', activation='relu', kernel_initializer='he_normal')(y)
y = Convolution2D(filters=256, kernel_size=3, strides=1, padding='same', activation='relu', kernel_initializer='he_normal')(y)
y = MaxPooling2D(pool_size=2, strides=2, padding='same')(y)
y = Flatten()(y)
y = Dropout(0.5)(y)
y = Dense(units=nb_classes, activation='softmax', kernel_initializer='he_normal')(y)

model1 = Model(inputs=x, outputs=y, name='model1')
model1.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy'])
model1.fit(X_train,Y_train,nb_epoch=10,batch_size=32)
loss,accuracy=model1.evaluate(X_test,Y_test)
print('test loss',loss)
print('accuracy',accuracy)

这是实验结果：