pytorch 图像分类数据集（Fashion-MNIST）

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import time
import sys
sys.path.append("..")  #导入d2lzh_pytorch
import d2lzh_pytorch as d2l   #导入所需要的包和模块

mnist_train =torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=True, download=True, transform=transforms.ToTensor())
#用torchvision的torchvision.datasets来下载数据集 通过参数train来指定训练数据集或测试数据集
#用transform=transform.ToTensor（）将所有数据转换为Tensor (不进行转换 换回的为PIL图片)
mnist_test =torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=False, download=True, transform=transforms.ToTensor())

print(type(mnist_train))
print(len(mnist_train), len(mnist_test)) #获取数据集的大小
输出结果：

<class 'torchvision.datasets.mnist.FashionMNIST'>

60000 10000

feature, label = mnist_train[0]  #通过下标来访问任意一个样本
print(feature.shape, label)  # Channel x Height X Width

输出结果：torch.Size([1, 28, 28]) 9

#1 28 28 C*H*W 第一维通道数 数据集为灰度图像 所以通道数为1  后面为高和宽

def get_fashion_mnist_labels(labels):
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress','coat','sandal', 'shirt', 'sneaker', 'bag', 'ankleboot']
    return [text_labels[int(i)] for i in labels]
#将数值标签转换为相应的文本标签

#定义可以在一行里画出多张图像和对应标签
def show_fashion_mnist(images, labels):
    #d2l.use_svg_display()

    _, figs = plt.subplots(1, len(images), figsize=(12, 12))
    for f, img, lbl in zip(figs, images, labels):
        f.imshow(img.view((28, 28)).numpy())
        f.set_title(lbl)
        f.axes.get_xaxis().set_visible(False)
        f.axes.get_yaxis().set_visible(False)
    plt.show()

X, y = [], []
for i in range(5):
    X.append(mnist_train[i][0])
    y.append(mnist_train[i][1])
show_fashion_mnist(X, get_fashion_mnist_labels(y))

batch_size = 256
if sys.platform.startswith('win'):
    num_workers = 0 #0表示不用额外的进程来加速读取数据
else:
    num_workers = 4 #设置4个进程读取数据
train_iter = torch.utils.data.DataLoader(mnist_train,batch_size=batch_size, shuffle=True, num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(mnist_test,batch_size=batch_size, shuffle=False, num_workers=num_workers)
#PyTorch的DataLoader中⼀个很⽅便的功能是允许使⽤多进程来加速数据读取

start = time.time()
for X, y in train_iter:
    continue
print('%.2f sec' % (time.time() - start))  #查看读取⼀遍训练数据需要的时间

输出结果：4.99 sec （不是一个确定值）