Keras 世上无难事只要肯放弃（1）

 

所有的内容都是从Keras中文文档看的

重新打一遍是因为想督促自己

不知道能坚持多久。

 

Keras sequential顺序模型

顺序模型是多个网络层的线性堆栈。

from keras.models import Sequential
from keras.layers import Dense,Activation

model = Sequential([
    Dense(32,input_shape=(784,)),
    Activation('relu'),
    Dense(10),
    Activation('softmax'),
])

也可以使用.add()方法

model = Sequential()
model.add(Dense(32,input_dim=784))
model.add(Activation('relu')

model.add(Dense(32,input_shape(784,)))和

model.add(Dense(32,input_dim=784))等价

 

模型编译

训练模型之前需要配置学习过程，由compile方法完成，它接收三个参数：

优化器optimizer

损失函数loss

评估标准metrics

# 多分类问题
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

# 二分类问题
model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

# 均方误差回归问题
model.compile(optimizer='rmsprop',
              loss='mse')

# 自定义评估标准函数
import keras.backend as K

def mean_pred(y_true, y_pred):
    return K.mean(y_pred)

model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy', mean_pred])

模型训练

Keras在numpy矩阵上进行训练，会使用到fit函数

# 对于具有 2 个类的单输入模型（二进制分类）：

model = Sequential()
model.add(Dense(32, activation='relu', input_dim=100))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

# 生成虚拟数据
import numpy as np
data = np.random.random((1000, 100))
labels = np.random.randint(2, size=(1000, 1))

# 训练模型，以 32 个样本为一个 batch 进行迭代
model.fit(data, labels, epochs=10, batch_size=32)

# 对于具有 10 个类的单输入模型（多分类分类）：

model = Sequential()
model.add(Dense(32, activation='relu', input_dim=100))
model.add(Dense(10, activation='softmax'))
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

# 生成虚拟数据
import numpy as np
data = np.random.random((1000, 100))
labels = np.random.randint(10, size=(1000, 1))

# 将标签转换为分类的 one-hot 编码
one_hot_labels = keras.utils.to_categorical(labels, num_classes=10)

# 训练模型，以 32 个样本为一个 batch 进行迭代
model.fit(data, one_hot_labels, epochs=10, batch_size=32)

样例  这个感觉很重要的样子！！

基于多层感知机的softmax多分类

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout

# 生成虚拟数据
x_train = np.random.random((1000, 20))
y_train = np.random.randint(2, size=(1000, 1))
x_test = np.random.random((100, 20))
y_test = np.random.randint(2, size=(100, 1))

model = Sequential()
model.add(Dense(64, input_dim=20, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

model.fit(x_train, y_train,
          epochs=20,
          batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)

 基于多层感知机的二分类：

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout

# 生成虚拟数据
x_train = np.random.random((1000, 20))
y_train = np.random.randint(2, size=(1000, 1))
x_test = np.random.random((100, 20))
y_test = np.random.randint(2, size=(100, 1))

model = Sequential()
model.add(Dense(64, input_dim=20, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

model.fit(x_train, y_train,
          epochs=20,
          batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)

类似VGG的卷积神经网络

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import SGD

# 生成虚拟数据
x_train = np.random.random((100, 100, 100, 3))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
x_test = np.random.random((20, 100, 100, 3))
y_test = keras.utils.to_categorical(np.random.randint(10, size=(20, 1)), num_classes=10)

model = Sequential()
# 输入: 3 通道 100x100 像素图像 -> (100, 100, 3) 张量。
# 使用 32 个大小为 3x3 的卷积滤波器。
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))

sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)

model.fit(x_train, y_train, batch_size=32, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=32)

基于LSTM的序列分类

from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import Embedding
from keras.layers import LSTM

max_features = 1024

model = Sequential()
model.add(Embedding(max_features, output_dim=256))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

model.fit(x_train, y_train, batch_size=16, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=16)