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

mnist_train =torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=True, download=True, transform=transforms.ToTensor())
#用torchvision的torchvision.datasets來下載數據集 通過參數train來指定訓練數據集或測試數據集                    
#用transform=transform.ToTensor（）將所有數據轉換為Tensor (不進行轉換 換回的為PIL圖片)
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)) #獲取數據集的大小
輸出結果：

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

60000 10000

feature, label = mnist_train[0]  #通過下標來訪問任意一個樣本
print(feature.shape, label)  # Channel x Height X Width

輸出結果：torch.Size([1, 28, 28]) 9

#1 28 28 C*H*W 第一維通道數 數據集為灰度影像 所以通道數為1  後面為高和寬

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]
#將數值標籤轉換為相應的文本標籤


#定義可以在一行里畫出多張影像和對應標籤
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表示不用額外的進程來加速讀取數據
else:
    num_workers = 4 #設置4個進程讀取數據
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中⼀個很⽅便的功能是允許使⽤多進程來加速數據讀取

start = time.time()
for X, y in train_iter:
    continue
print('%.2f sec' % (time.time() - start))  #查看讀取⼀遍訓練數據需要的時間

輸出結果：4.99 sec （不是一個確定值）