实战分类模型的全部代码，tensorflow2.0可直接运行，包含有数据归一化和tensorboard

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)
fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

print(x_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

# x = (x - u) / std 数据归一化

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
# x_train: [None, 28, 28] -> [None, 784]
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)
x_valid_scaled = scaler.transform(
    x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)
x_test_scaled = scaler.transform(
    x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)

#模型构建
# tf.keras.models.Sequential()

"""
model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28, 28]))
model.add(keras.layers.Dense(300, activation="relu"))
model.add(keras.layers.Dense(100, activation="relu"))
model.add(keras.layers.Dense(10, activation="softmax"))
"""
# relu: y = max(0, x)
# softmax: 将向量变成概率分布. x = [x1, x2, x3], 
#          y = [e^x1/sum, e^x2/sum, e^x3/sum], sum = e^x1 + e^x2 + e^x3
model = keras.models.Sequential([
    keras.layers.Flatten(input_shape=[28, 28]),
    keras.layers.Dense(300, activation='relu'),
    keras.layers.Dense(100, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])



# 编译：reason for sparse: y->index. y->one_hot->[] 
model.compile(loss="sparse_categorical_crossentropy",
              optimizer = keras.optimizers.SGD(0.001),
              metrics = ["accuracy"])

# Tensorboard（文件夹）, earlystopping, ModelCheckpoint（文件名）
logdir = os.path.join("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),#保存最好的模型，默认保存最近的
    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
"""添加callback是在训练过程中做监听，所以是在fit函数中进行添加
    添加方式：定义一个callbacks数组，
    在fit函数中把数组作为参数传进来
"""
#模型训练
history = model.fit(x_train_scaled, y_train, epochs=10,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

#在jupyter中画图显示history中值的变化
def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))#图的大小设成8和5
    plt.grid(True) #显示网格
    plt.gca().set_ylim(0, 1) #y坐标轴范围
    plt.show()

plot_learning_curves(history)

#在测试集上测试
model.evaluate(x_test_scaled, y_test, verbose=0)#verbose=0决定了是否显示进度条
#显示：[loss, accuracy]