Tesorflow2.0卷积神经网络实例之Fashion MINST数据集处理

本实例主要参考博客https://blog.csdn.net/cos_lee/article/details/93882520，里面有数据集的下载链接，讲解了加载数据集的方法，请大家阅读，这里不再赘述。唯一不同的是，此博客采用普通的三层全连接神经网络处理数据，而本例采用卷积神经网络。

关于安装tensorflow，推荐大家使用anaconda navigator下载，用字符界面容易出错。

本例中使用的Fashion MINST数据是四个.gz文件，如下图。文件路径根据实际情况设定。

代码如下。卷积神经网络训练时间很长，请耐心等待。

import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
import gzip
import math

def get_data():
    # 文件获取
    train_image = r"E:/Data/fashion_minist/train-images-idx3-ubyte.gz"
    test_image = r"E:/Data/fashion_minist/t10k-images-idx3-ubyte.gz"
    train_label = r"E:/Data/fashion_minist/train-labels-idx1-ubyte.gz"
    test_label = r"E:/Data/fashion_minist/t10k-labels-idx1-ubyte.gz" #文件路径
    paths = [train_label, train_image, test_label,test_image]

    with gzip.open(paths[0], 'rb') as lbpath:
        y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)

    with gzip.open(paths[1], 'rb') as imgpath:
        x_train = np.frombuffer(
            imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)

    with gzip.open(paths[2], 'rb') as lbpath:
        y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)

    with gzip.open(paths[3], 'rb') as imgpath:
        x_test = np.frombuffer(
            imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)

    return (x_train, y_train), (x_test, y_test)

(train_images, train_labels), (test_images, test_labels) = get_data()

if __name__ == '__main__':
    
    class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
                   'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
    #数据归一化
    train_images = train_images / 255.0
    test_images = test_images / 255.0
    
    num_train_examples=len(train_images)
    num_test_examples=len(test_images)
    
    '''
    #打印其中一个样本
    image=test_images[1]
    plt.figure()
    plt.imshow(image,cmap=plt.cm.binary)
    plt.colorbar()
    plt.grid(False)
    plt.show()
    
    #打印前25个样本
    plt.figure(figsize=(10,10))
    for i in range(25):
        plt.subplot(5,5,i+1)
        plt.xticks([])
        plt.yticks([])
        plt.grid(False)
        #print(train_images[i])
        plt.imshow(train_images[i], cmap=plt.cm.binary)
        plt.xlabel(class_names[train_labels[i]])
    plt.show()
     '''
    
    #卷积神经网络 
    model = tf.keras.Sequential([
        #卷积层，输出结点32，卷积核3*3，边界补零，激活函数采用relu，
        #输入格式28*28*1，图像是28*28像素，1个卷积核，下同
        tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu,
        input_shape=(28, 28, 1)),
        #池化层，池化维度2*2，步长为2，下同
        tf.keras.layers.MaxPooling2D((2, 2), strides=2),
        tf.keras.layers.Conv2D(64, (3,3), padding='same', activation=tf.nn.relu),
        tf.keras.layers.MaxPooling2D((2, 2), strides=2),
        #将数据压为一维
        tf.keras.layers.Flatten(),
        #最后两层是全连接层
        tf.keras.layers.Dense(128, activation=tf.nn.relu),
        tf.keras.layers.Dense(10,  activation=tf.nn.softmax)
    ])
    
        
    
    #转换数据格式，与卷积神经网络的输入相适应
    train_reshaped=np.reshape(train_images,newshape=(len(train_images),28,28,1))
    test_reshaped=np.reshape(test_images,newshape=(len(test_images),28,28,1))
    
    #模型编译
    model.compile(optimizer='adam', 
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
    
    
    #模型训练
    model.fit(train_reshaped, train_labels, epochs=50)
    #模型测试
    test_loss, test_acc = model.evaluate(test_reshaped, test_labels)
    print('Test accuracy:', test_acc)