006.图像分类数据集

MNIST 数据集是图像分类中广泛使用的数据集之一，但作为基准数据集过于简单。我们将使用类似但更复杂的 Fashion-MNIST 数据集

import torch
import torchvision
from torch.utils import data
from torchvision import transforms
from d2l import torch as d2l
 
d2l.use_svg_display()

读取数据集

通过框架中的内置函数将 Fashion-MNIST 数据集下载并读取到内存中

# 通过 ToTensor 实例将图像数据从 PI L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 0～1 之间
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)
"""
(60000, 10000)
"""

mnist_train[0][0].shape, mnist_train[0][1]
# x：长宽 28 的灰度图；y：类别为 9
"""
(torch.Size([1, 28, 28]), 9)
"""

可视化数据集

def get_fashion_mnist_labels(labels):
	"""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):
	"""绘制图像列表"""
	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

读取一小批量数据，大小为 batch_size

batch_size = 256
 
def get_dataloader_workers():
    """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())
 
# 看一下读取训练数据所需的时间
timer = d2l.Timer()
for X, y in train_iter:
    continue
f'{timer.stop():.2f} sec'
"""
'3.37 sec'
"""

整合所有组件

定义 load_data_fashion_mnist 函数，用于获取和读取 Fashion-MNIST 数据集。这个函数返回训练集和验证集的数据迭代器。可选参数 resize，用来将图像大小调整为另一种形状

def load_data_fashion_mnist(batch_size, resize=None):
	"""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
"""