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

%matplotlib inline
import torch
import torchvision
from torch.utils import data
from torchvision import transforms
from d2l import torch as d2l

d2l.use_svg_display()

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

数据集下载

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)

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ../data/FashionMNIST/raw/train-images-idx3-ubyte.gz


100.0%


Extracting ../data/FashionMNIST/raw/train-images-idx3-ubyte.gz to ../data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to ../data/FashionMNIST/raw/train-labels-idx1-ubyte.gz


100.6%


Extracting ../data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to ../data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to ../data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz


71.3%IOPub message rate exceeded.
The notebook server will temporarily stop sending output
to the client in order to avoid crashing it.
To change this limit, set the config variable
`--NotebookApp.iopub_msg_rate_limit`.

Current values:
NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)
NotebookApp.rate_limit_window=3.0 (secs)

mnist_train[0][0].shape

torch.Size([1, 28, 28])

两个可视化数据集的函数

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):  
    """Plot a list of images."""
    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):
            ax.imshow(img.numpy())
        else:
            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

几个样本的图像及其相应的标签

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())

timer = d2l.Timer()
for X, y in train_iter:
    continue
f'{timer.stop():.2f} sec'

'1.40 sec'

定义 load_data_fashion_mnist 函数

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=False)
    mnist_test = torchvision.datasets.FashionMNIST(root="../data",
                                                   train=False,
                                                   transform=trans,
                                                   download=False)
    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