06 加入批归一化的深度学习

'''分类问题'''
import tensorflow as tf
import matplotlib as mpl
import matplotlib.pyplot as plt

import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
from tensorflow import keras
#导入数据
fashion_mnist = keras.datasets.fashion_mnist
(x_train_all,y_train_all),(x_test,y_test) = fashion_mnist.load_data()#训练集
x_valid,x_train = x_train_all[:5000],x_train_all[5000:]              #前5000张为验证集，5000张之后的为训练集
y_valid,y_train = y_train_all[:5000],y_train_all[5000:]

#对数据做归一化
from sklearn.preprocessing import  StandardScaler
scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1,1)).reshape(-1,28,28)
x_valid_scaled = scaler.fit_transform(
    x_valid.astype(np.float32).reshape(-1,1)).reshape(-1,28,28)
x_test_scaled = scaler.fit_transform(
    x_test.astype(np.float32).reshape(-1,1)).reshape(-1,28,28)

#定义训练模型
model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28,28]))
#添加20层的神经网络
for _ in range(20):
    model.add(keras.layers.Dense(100,activation="relu"))
    model.add(keras.layers.BatchNormalization())
    '''
    激活函数是放在批归一化之前还是之后（另一种写法）
    model.add(keras.layers.Dense(100)
    model.add(keras.layer.BatchNormalization())
    model.add(keras.layers.Activation('relu'))
    '''
model.add(keras.layers.Dense(10,activation="softmax"))
model.compile(loss="sparse_categorical_crossentropy",
              optimizer = "sgd",#因为用sgd梯度下降法会导致陷入局部最小值点
              metrics = ['accuracy'])
model.summary()
#回调函数
logdir = "./dnn-bn-callbacks"
if not os.path.exists(logdir):
    os.mkdir(logdir)
output_model_file = os.path.join(logdir,"fashion_mnist_model.h5")
callbacks = {
    keras.callbacks.TensorBoard(logdir),
    keras.callbacks.ModelCheckpoint(output_model_file,
                                    save_best_only="True"),
    keras.callbacks.EarlyStopping(patience = 5, min_delta = 1e-3),
}

#开始训练
history = model.fit(x_train_scaled,y_train,epochs = 10,validation_data = (x_valid_scaled,y_valid))
#画图展示准确度
def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8,5))
    plt.grid(True)
    plt.gca().set_ylim(0,3)
    plt.show()
plot_learning_curves(history)
#在测试集上的准确度
model.evaluate(x_test_scaled,y_test)
'''
批归一化在一定程度上可以缓解梯度消失
'''

运行结果：