TensorFlow 数据集归一化，测试结果

TensorFlow 数据集归一化，测试结果

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
import tensorflow as tf
from tensorflow_core.python import keras
from sklearn.preprocessing import StandardScaler

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')

# 0.打印导入模块的版本
print(tf.__version__)
print(sys.version_info)
for module in mpl, np, sklearn, pd, tf, keras:
    print("%s version:%s" % (module.__name__, module.__version__))

# 1.加载fashion_mnist数据集
fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()

# 2.拆分验证集, 训练集
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

# 3.打印 训练集，验证集, 测试集
print(x_train.shape, y_train.shape)
print(x_valid.shape, y_valid.shape)
print(x_test.shape, y_test.shape)

print("min:", np.min(x_train), "max:", np.max(x_train))

# 4.数据归一化
# x = (x - u) / std
scaler = StandardScaler()

# x_train:[None, 28, 28] -> [None, 784] -> [None, 28, 28]
x_train_scaled = scaler.fit_transform(x_train.astype(np.float32).reshape(-1, 1))
x_train_scaled = x_train_scaled.reshape(-1, 28, 28)

x_valid_scaled = scaler.transform(x_valid.astype(np.float32).reshape(-1, 1))
x_valid_scaled = x_valid_scaled.reshape(-1, 28, 28)

x_test_scaled = scaler.transform(x_test.astype(np.float32).reshape(-1, 1))
x_test_scaled = x_test_scaled.reshape(-1, 28, 28)

print("min:", np.min(x_train_scaled), "max:", np.max(x_train_scaled))


def main():

    # 1.网络模型构建
    model = keras.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")
    ])

    # 2.编译模型
    # reason for sparse: y->index => y->one_hot->[]
    model.compile(loss="sparse_categorical_crossentropy",  # 损失函数
                  optimizer="sgd",                         # 模型优化方法
                  metrics=["accuracy"])                    # 指标 准确度

    # 3.打印模型
    model.summary()

    # 4.训练模型
    history = model.fit(x_train_scaled, y_train, epochs=10,
                        validation_data=(x_valid_scaled, y_valid))

    # 5.测试集
    model.evaluate(x_test_scaled, y_test)


if __name__ == '__main__':
    main()