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塊
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 數據集為灰度圖像 所以通道數為1 后面為高和寬
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] #將數值標簽轉換為相應的文本標簽
#定義可以在一行里畫出多張圖像和對應標簽
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）
