第三章神经网络八股
3.1搭建神经网络sequential（上层输出就是下层输入的顺序网络结构）
使用tensorflow的API:tf.keras搭建网络六步法：
第一步：import相关模块。
第二步：train和test数据集。
第三步：model = tf.keras.models.Sequential()。
第四步：model.compile()配置训练方法，选择优化器，损失函数和评价指标。
第五步：model.fit()执行训练过程，告知训练集的输入和标签，batch大小和epoch迭代次数。
第六步：model.summary()打印网络结构，统计参数。
下面仔细介绍这些函数的使用方法：
model = tf.keras.models.Sequential ([ 网络结构 ]) #描述各层网络
拉直层: tf.keras.layers.Flatten( )
全连接层: tf.keras.layers.Dense(神经元个数, activation= "激活函数“ ,
kernel_regularizer=哪种正则化)
activation(字符串给出)可选: relu、 softmax、 sigmoid 、tanh
kernel_regularizer可选: tf.keras.regularizers.l1()、tf.keras.regularizers.l2()
卷积层: tf.keras.layers.Conv2D(filters = 卷积核个数, kernel_size = 卷积核尺寸,
strides = 卷积步长， padding = " valid" or "same")
LSTM层: tf.keras.layers.LSTM()
model.compile(optimizer = 优化器, loss = 损失函数
Optimizer可选:
metrics = [“准确率”] )
‘sgd’ or tf.keras.optimizers.SGD (lr=学习率,momentum=动量参数)
‘adagrad’ or tf.keras.optimizers.Adagrad (lr=学习率)
‘adadelta’ or tf.keras.optimizers.Adadelta (lr=学习率)
‘adam’ or tf.keras.optimizers.Adam (lr=学习率, beta_1=0.9, beta_2=0.999)
loss可选:
‘mse’ or tf.keras.losses.MeanSquaredError()
‘sparse_categorical_crossentropy’ or tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False
Metrics可选:
‘accuracy’:y_和y都是数值，如y_=[1] y=[1]
‘categorical_accuracy’ :y_和y都是独热码(概率分布)，如y_=[0,1,0] y=[0.256,0.695,0.048]
‘sparse_categorical_accuracy’ :y_是数值，y是独热码(概率分布),如y_=[1] y=[0.256,0.695,0.048]
model.fit (训练集的输入特征, 训练集的标签, batch_size= , epochs= ,
validation_data=(测试集的输入特征，测试集的标签), validation_split=从训练集划分多少比例给测试集， validation_freq = 多少次epoch测试一次)
下面给出具体的代码实现：
import tensorflow as tf
from sklearn import datasets
import numpy as np # 第一步
x_train = datasets.load_iris().data # 导入数据
y_train = datasets.load_iris().target # 导入标签
np.random.seed(116) # 打乱数据集
np.random.shuffle(x_train)
np.random.seed(116)
np.random.shuffle(y_train)
tf.random.set_seed(116) # 第二步
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())
]) # 第三步
model.compile(optimezer=tf.keras.optimizers.SGD(lr=0.1),
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy']) # 第四步
model.fit(x_train, y_train, batch_size=32, epochs=500, validation_split=0.2, validation_freq=20) # 第五步
model.summary() # 第六步
3.2搭建神经网络class（跳连的非顺序网络结构）
除了第三步其余与3.1相同。
class MyModel(Model) model = MyModel
class MyModel(Model):
def init(self):
super(MyModel, self).init()
定义网络结构块
def call(self, x):
调用网络结构块，实现前向传播
return y
model = MyModel()
下面给出代码实现：
import tensorflow as tf
from sklearn import datasets
from tensorflow.keras import Model
from tensorflow.keras.layers import Dense
import numpy as np # 第一步
x_train = datasets.load_iris().data # 导入数据
y_train = datasets.load_iris().target # 导入标签
np.random.seed(116) # 打乱数据集
np.random.shuffle(x_train)
np.random.seed(116)
np.random.shuffle(y_train)
tf.random.set_seed(116) # 第二步
class IrisModel(Model):
def __init__(self):
super(IrisModel, self).__init__()
self.d1 = Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())
def call(self, x):
y = self.d1(x)
return y
# 第三步
model = IrisModel()
model.compile(optimezer=tf.keras.optimizers.SGD(lr=0.1),
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy']) # 第四步
model.fit(x_train, y_train, batch_size=32, epochs=500, validation_split=0.2, validation_freq=20) # 第五步
model.summary() # 第六步
3.3mnist数据集
下面给出基于mnist数据集的sequential和class实现方法：
sequential：
import tensorflow as tf
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train/255.0, x_test/255.0 # 因为原数据为1-255，进行归一化处理
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(), # 拉伸原数据
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()
class:
import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras import Model
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0 # 因为原数据为1-255，进行归一化处理
class MnistModel(Model):
def __init__(self):
super(MnistModel, self).__init__()
self.flatten = Flatten()
self.d1 = Dense(128, activation='relu')
self.d2 = Dense(10, activation='softmax')
def call(self, x):
x = self.flatten(x)
x = self.d1(x)
y = self.d2(x)
return y
model = MnistModel()
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()
3.4使用fashion数据集进行练习
import tensorflow as tf
fashion = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion.load_data()
x_train, x_test = x_train/255.0, x_test/255.0
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()
import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras import Model
fashion = tf.keras.datasets.fashion_mnist
(x_train, y_train),(x_test, y_test) = fashion.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
class MnistModel(Model):
def __init__(self):
super(MnistModel, self).__init__()
self.flatten = Flatten()
self.d1 = Dense(128, activation='relu')
self.d2 = Dense(10, activation='softmax')
def call(self, x):
x = self.flatten(x)
x = self.d1(x)
y = self.d2(x)
return y
model = MnistModel()
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()