图像去雾毕业论文准备09-深度学习框架（tensorflow2.0）——超级详细（手写体数据加载、独热编码one-hot）

小咪咪 2023-01-02 05:24 118阅读 0赞

#!/usr/bin/python3.6
    # -*- coding: utf-8 -*-
    # @Time    : 2021/1/3 16:58
    # @Author  : ptg
    # @Email   : zhxwhchina@163.com
    # @File    : tensorflow2.0.py
    # @Software: PyCharm
    
    # 测试是否安装成功
    import tensorflow as tf
    import os
    import pandas as pd
    import matplotlib.pyplot as plt
    import numpy as np
    
    # 加载数据集
    (train_image,train_lable),(test_image,test_label)= tf.keras.datasets.fashion_mnist.load_data()
    
    print(train_image.shape)
    print(train_lable.shape)
    plt.imshow(train_image[0])
    plt.show()
    print(np.max(train_image))
    
    train_image = train_image / 255
    test_image = test_image/255
    
    print(train_image.shape)
    
    model = tf.keras.Sequential()
    model.add(tf.keras.layers.Flatten(input_shape=(28,28)))
    model.add(tf.keras.layers.Dense(128,activation='relu'))
    model.add(tf.keras.layers.Dense(10,activation='softmax'))
    
    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['acc'])
    model.fit(train_image,train_lable,epochs=5)
    a = model.evaluate(test_image,test_label)
    print(a)

## 独热编码 ##

![在这里插入图片描述][20210104221325287.png]

[20210104221325287.png]: /images/20221120/4f436a7a593c4ced8c5b5ac14d4984d7.png