学习笔记：动手学深度学习 11 图像分类数据集

#数据库导入
import torch
import torchvision
from torch.utils import data
from torchvision import transforms
from d2l import torch as d2l
import matplotlib.pyplot as plt
d2l.use_svg_display()  #使用svg呈现

Backend Qt5Agg is interactive backend. Turning interactive mode on. #这个我没有管，也不是报错

# 通过ToTensor实例将图像数据从PIL类型变换成32位浮点数格式
# 并除以255使得所有像素的数值均在0到1之间
#训练数据和验证数据下载
trans = transforms.ToTensor()
mnist_train = torchvision.datasets.FashionMNIST(
    root="../data", train=True, transform=trans, download=True)
mnist_test = torchvision.datasets.FashionMNIST(
    root="../data", train=False, transform=trans, download=True)
len(mnist_train), len(mnist_test)
Out[6]: (60000, 10000)
#每个输入图像的高度和宽度均为28像素。数据集由灰度图像组成，其通道数为1。
mnist_train[0][0].shape
Out[7]: torch.Size([1, 28, 28])
"""函数用于在数字标签索引及其文本名称之间进行转换"""
def get_fashion_mnist_labels(labels):  #@save
    """返回Fashion-MNIST数据集的文本标签。"""
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
                   'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
    return [text_labels[int(i)] for i in labels]

def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5):  #@save
    """创建一个函数来可视化这些样本"""
    figsize = (num_cols * scale, num_rows * scale)
    _, axes = d2l.plt.subplots(num_rows, num_cols, figsize=figsize)
    axes = axes.flatten()
    for i, (ax, img) in enumerate(zip(axes, imgs)):
        if torch.is_tensor(img):
            # 图片张量
            ax.imshow(img.numpy())
        else:
            # PIL图片
            ax.imshow(img)
        ax.axes.get_xaxis().set_visible(False)
        ax.axes.get_yaxis().set_visible(False)
        if titles:
            ax.set_title(titles[i])
    return axes
X, y = next(iter(data.DataLoader(mnist_train, batch_size=18)))
show_images(X.reshape(18, 28, 28), 2, 9, titles=get_fashion_mnist_labels(y));
"""读取小批量"""
batch_size = 256
def get_dataloader_workers():  #@save
    """使用4个进程来读取数据。"""
    return 4
train_iter = data.DataLoader(mnist_train, batch_size, shuffle=True,
                             num_workers=get_dataloader_workers())
timer = d2l.Timer()
for X, y in train_iter:
    continue
f'{timer.stop():.2f} sec'
Out[12]: '4.51 sec'
def load_data_fashion_mnist(batch_size, resize=None):  #@save
    """下载Fashion-MNIST数据集，然后将其加载到内存中。"""
    trans = [transforms.ToTensor()]
    if resize:
        trans.insert(0, transforms.Resize(resize))
    trans = transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(
        root="../data", train=True, transform=trans, download=True)
    mnist_test = torchvision.datasets.FashionMNIST(
        root="../data", train=False, transform=trans, download=True)
    return (data.DataLoader(mnist_train, batch_size, shuffle=True,
                            num_workers=get_dataloader_workers()),
            data.DataLoader(mnist_test, batch_size, shuffle=False,
                            num_workers=get_dataloader_workers()))
train_iter, test_iter = load_data_fashion_mnist(32, resize=64)
for X, y in train_iter:
    print(X.shape, X.dtype, y.shape, y.dtype)
    break
    
torch.Size([32, 1, 64, 64]) torch.float32 torch.Size([32]) torch.int64