torchvision.datasets.cifar10

torchvision.datasets.cifar10 是 PyTorch 中的一个数据集，其中包含了 60,000 张 32x32 的彩色图像，分成 10 个类别，每类 6000 张图像。这些图像来自 CIFAR-10 数据集，是用于图像识别的常用数据集之一。

相关问题

torchvision.datasets.CIFAR10

`torchvision.datasets.CIFAR10` 是一个 PyTorch 中的数据集类，它包含了 10 类不同类型的图片数据，例如飞机、汽车、鸟类、猫、鹿、狗、青蛙、马、船和卡车。每一个图片都是 $32 \times 32$ 的彩色图片，可以用来进行图像分类任务的训练和测试。这个数据集通常用于计算机视觉领域的研究和实验。你可以使用 `torchvision.datasets.CIFAR10` 类来加载 CIFAR-10 数据集，然后将其转换为 PyTorch 的张量形式，以便进行模型训练和测试。

torchvision.datasets.CIFAR10源码

以下是torchvision.datasets.CIFAR10的源码：

import torch.utils.data as data
from PIL import Image
import os
import os.path
import numpy as np
import pickle


class CIFAR10(data.Dataset):
    """`CIFAR10 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.

    Args:
        root (string): Root directory of dataset where directory
            ``cifar-10-batches-py`` exists or will be downloaded to if download is set to True.
        train (bool, optional): If True, creates dataset from training set, otherwise
            creates from test set.
        transform (callable, optional): A function/transform that takes in an PIL image
            and returns a transformed version. E.g, ``transforms.RandomCrop``
        target_transform (callable, optional): A function/transform that takes in the
            target and transforms it.

    Returns:
        tuple: (image, target) where target is index of the target class.
    """

    base_folder = 'cifar-10-batches-py'
    url = "https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz"
    filename = "cifar-10-python.tar.gz"
    tgz_md5 = 'c58f30108f718f92721af3b95e74349a'
    train_list = [
        ['data_batch_1', 'c99cafc152244af753f735de768cd75f'],
        ['data_batch_2', 'd4bba439e000b95fd0a9bffe97cbabec'],
        ['data_batch_3', '54ebc095f3ab1f03828d0aae7e51cd9d'],
        ['data_batch_4', '634d18415352ddfa80567beed471001a'],
        ['data_batch_5', '482c414d41f54cd18b22e5b47cb7c3cb'],
    ]

    test_list = [
        ['test_batch', '40351d587109b95175f43aff81a1287e'],
    ]

    def __init__(self, root, train=True,
                 transform=None, target_transform=None,
                 download=False):
        self.root = os.path.expanduser(root)
        self.transform = transform
        self.target_transform = target_transform
        self.train = train  # training set or test set

        if download:
            self.download()

        if not self._check_integrity():
            raise RuntimeError('Dataset not found or corrupted.' +
                               ' You can use download=True to download it')

        if self.train:
            downloaded_list = self.train_list
        else:
            downloaded_list = self.test_list

        self.data = []
        self.targets = []

        # now load the picked numpy arrays
        for file_name, checksum in downloaded_list:
            file_path = os.path.join(self.root, self.base_folder, file_name)
            with open(file_path, 'rb') as f:
                if 'meta' in file_name:
                    data_dict = pickle.load(f, encoding='latin1')
                    self.classes = data_dict['label_names']
                else:
                    data_dict = pickle.load(f, encoding='latin1')
                    self.data.append(data_dict['data'])
                    self.targets.extend(data_dict['labels'])

        self.data = np.vstack(self.data).reshape(-1, 3, 32, 32)
        self.data = self.data.transpose((0, 2, 3, 1))  # convert to HWC

    def __getitem__(self, index):
        """
        Args:
            index (int): Index

        Returns:
            tuple: (image, target) where target is index of the target class.
        """
        img, target = self.data[index], self.targets[index]

        # doing this so that it is consistent with all other datasets
        # to return a PIL Image
        img = Image.fromarray(img)

        if self.transform is not None:
            img = self.transform(img)

        if self.target_transform is not None:
            target = self.target_transform(target)

        return img, target

    def __len__(self):
        return len(self.data)

    def _check_integrity(self):
        root = self.root
        for fentry in (self.train_list + self.test_list):
            filename, md5 = fentry[0], fentry[1]
            fpath = os.path.join(root, self.base_folder, filename)
            if not check_integrity(fpath, md5):
                return False
        return True

    def download(self):
        import tarfile

        if self._check_integrity():
            print('Files already downloaded and verified')
            return

        download_url(self.url, self.root, self.filename, self.tgz_md5)

        # extract file
        with tarfile.open(os.path.join(self.root, self.filename), "r:gz") as tar:
            tar.extractall(path=self.root)

        print('Done!')


class CIFAR100(CIFAR10):
    """`CIFAR100 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.

    This is a subclass of the `CIFAR10` Dataset.
    """

    base_folder = 'cifar-100-python'
    url = "https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz"
    filename = "cifar-100-python.tar.gz"
    tgz_md5 = 'eb9058c3a382ffc7106e4002c42a8d85'
    train_list = [
        ['train', '16019d7e3df5f24257cddd939b257f8d'],
    ]

    test_list = [
        ['test', 'f0ef6b0ae62326f3e7ffdfab6717acfc'],
    ]

    def __init__(self, root, train=True,
                 transform=None, target_transform=None,
                 download=False):
        super(CIFAR100, self).__init__(root, train=train,
                                       transform=transform,
                                       target_transform=target_transform,
                                       download=download)

该代码定义了CIFAR10和CIFAR100数据集的类，这些数据集是用于图像分类任务的标准数据集之一。每个数据集都有一个训练集和一个测试集，每个图像都有一个标签，表示它所属的类别。

这些类继承自torch.utils.data.Dataset类，并实现了__getitem__和__len__方法。它们还提供了下载和检查数据集完整性的方法。

在初始化阶段，数据集从pickle文件中加载数据和标签，并将其存储在self.data和self.targets中。__getitem__方法返回图像和标签的元组，__len__方法返回数据集中图像的数量。