.. _sec_fashion_mnist:

图像分类数据集
==============


MNIST数据集 :cite:`LeCun.Bottou.Bengio.ea.1998`
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
:cite:`Xiao.Rasul.Vollgraf.2017`\ 。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-1-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-1-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-1-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-1-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-1-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    %matplotlib inline
    import sys
    from mxnet import gluon
    from d2l import mxnet as d2l
    
    d2l.use_svg_display()



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-1-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    %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()



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-1-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    %matplotlib inline
    import tensorflow as tf
    from d2l import tensorflow as d2l
    
    d2l.use_svg_display()



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-1-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    %matplotlib inline
    import warnings
    from d2l import paddle as d2l
    
    warnings.filterwarnings("ignore")
    import sys
    import paddle
    from paddle.vision import transforms
    
    d2l.use_svg_display()



.. raw:: html

    </div>



.. raw:: html

    </div>

读取数据集
----------

我们可以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。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-3-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-3-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-3-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-3-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-3-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    mnist_train = gluon.data.vision.FashionMNIST(train=True)
    mnist_test = gluon.data.vision.FashionMNIST(train=False)


.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    Downloading /opt/mxnet/datasets/fashion-mnist/train-images-idx3-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/fashion-mnist/train-images-idx3-ubyte.gz...
    Downloading /opt/mxnet/datasets/fashion-mnist/train-labels-idx1-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/fashion-mnist/train-labels-idx1-ubyte.gz...
    [07:01:09] ../src/storage/storage.cc:196: Using Pooled (Naive) StorageManager for CPU
    Downloading /opt/mxnet/datasets/fashion-mnist/t10k-images-idx3-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/fashion-mnist/t10k-images-idx3-ubyte.gz...
    Downloading /opt/mxnet/datasets/fashion-mnist/t10k-labels-idx1-ubyte.gz from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/dataset/fashion-mnist/t10k-labels-idx1-ubyte.gz...




.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-3-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    # 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0～1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)



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-3-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    mnist_train, mnist_test = tf.keras.datasets.fashion_mnist.load_data()



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-3-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    trans = transforms.ToTensor()
    mnist_train = paddle.vision.datasets.FashionMNIST(mode="train",
                                                      transform=trans)
    mnist_test = paddle.vision.datasets.FashionMNIST(mode="test", transform=trans)



.. raw:: html

    </div>



.. raw:: html

    </div>

Fashion-MNIST由10个类别的图像组成， 每个类别由\ *训练数据集*\ （train
dataset）中的6000张图像 和\ *测试数据集*\ （test
dataset）中的1000张图像组成。
因此，训练集和测试集分别包含60000和10000张图像。
测试数据集不会用于训练，只用于评估模型性能。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-5-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-5-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-5-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-5-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-5-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    len(mnist_train), len(mnist_test)




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (60000, 10000)





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-5-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    len(mnist_train), len(mnist_test)




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (60000, 10000)





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-5-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    len(mnist_train[0]), len(mnist_test[0])




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (60000, 10000)





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-5-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    len(mnist_train), len(mnist_test)




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (60000, 10000)





.. raw:: html

    </div>



.. raw:: html

    </div>

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。
为了简洁起见，本书将高度\ :math:`h`\ 像素、宽度\ :math:`w`\ 像素图像的形状记为\ :math:`h \times w`\ 或（\ :math:`h`,\ :math:`w`\ ）。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-7-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-7-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-7-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-7-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-7-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    mnist_train[0][0].shape




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (28, 28, 1)





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-7-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    mnist_train[0][0].shape




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

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





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-7-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    mnist_train[0][0].shape




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (28, 28)





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-7-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    mnist_train[0][0].shape




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    [1, 28, 28]





.. raw:: html

    </div>



.. raw:: html

    </div>

Fashion-MNIST中包含的10个类别，分别为t-shirt（T恤）、trouser（裤子）、pullover（套衫）、dress（连衣裙）、coat（外套）、sandal（凉鞋）、shirt（衬衫）、sneaker（运动鞋）、bag（包）和ankle
boot（短靴）。 以下函数用于在数字标签索引及其文本名称之间进行转换。

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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]

我们现在可以创建一个函数来可视化这些样本。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-11-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-11-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-11-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-11-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-11-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5):  #@save
        """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)):
            ax.imshow(img.asnumpy())
            ax.axes.get_xaxis().set_visible(False)
            ax.axes.get_yaxis().set_visible(False)
            if titles:
                ax.set_title(titles[i])
        return axes



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-11-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5):  #@save
        """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



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-11-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5):  #@save
        """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)):
            ax.imshow(img.numpy())
            ax.axes.get_xaxis().set_visible(False)
            ax.axes.get_yaxis().set_visible(False)
            if titles:
                ax.set_title(titles[i])
        return axes



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-11-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    #@save
    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 paddle.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



.. raw:: html

    </div>



.. raw:: html

    </div>

以下是训练数据集中前几个样本的图像及其相应的标签。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-13-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-13-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-13-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-13-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-13-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    X, y = mnist_train[:18]
    
    print(X.shape)
    show_images(X.squeeze(axis=-1), 2, 9, titles=get_fashion_mnist_labels(y));


.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (18, 28, 28, 1)



.. figure:: output_image-classification-dataset_e45669_80_1.svg




.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-13-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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));



.. figure:: output_image-classification-dataset_e45669_83_0.svg




.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-13-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    X = tf.constant(mnist_train[0][:18])
    y = tf.constant(mnist_train[1][:18])
    show_images(X, 2, 9, titles=get_fashion_mnist_labels(y));



.. figure:: output_image-classification-dataset_e45669_86_0.svg




.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-13-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    X, y = next(iter(paddle.io.DataLoader(mnist_train, batch_size=18)))
    show_images(X.reshape([18, 28, 28]), 2, 9, titles=get_fashion_mnist_labels(y));



.. figure:: output_image-classification-dataset_e45669_89_0.svg




.. raw:: html

    </div>



.. raw:: html

    </div>

读取小批量
----------

为了使我们在读取训练集和测试集时更容易，我们使用内置的数据迭代器，而不是从零开始创建。
回顾一下，在每次迭代中，数据加载器每次都会读取一小批量数据，大小为\ ``batch_size``\ 。
通过内置数据迭代器，我们可以随机打乱了所有样本，从而无偏见地读取小批量。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-15-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-15-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-15-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-15-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-15-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    batch_size = 256
    
    def get_dataloader_workers():  #@save
        """在非Windows的平台上，使用4个进程来读取数据"""
        return 0 if sys.platform.startswith('win') else 4
    
    # 通过ToTensor实例将图像数据从uint8格式变换成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
    transformer = gluon.data.vision.transforms.ToTensor()
    train_iter = gluon.data.DataLoader(mnist_train.transform_first(transformer),
                                       batch_size, shuffle=True,
                                       num_workers=get_dataloader_workers())



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-15-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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())



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-15-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    batch_size = 256
    train_iter = tf.data.Dataset.from_tensor_slices(
        mnist_train).batch(batch_size).shuffle(len(mnist_train[0]))



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-15-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    batch_size = 256
    
    def get_dataloader_workers():  #@save
        """使用4个进程来读取数据"""
        return 4
    
    train_iter = paddle.io.DataLoader(dataset=mnist_train,
                                      batch_size=batch_size,
                                      shuffle=True,
                                      return_list=True,
                                      num_workers=get_dataloader_workers())



.. raw:: html

    </div>



.. raw:: html

    </div>

我们看一下读取训练数据所需的时间。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-17-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-17-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-17-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-17-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-17-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

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




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    '1.89 sec'





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-17-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

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




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    '3.37 sec'





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-17-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

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




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    '0.31 sec'





.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-17-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

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




.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    '5.65 sec'





.. raw:: html

    </div>



.. raw:: html

    </div>

整合所有组件
------------

现在我们定义\ ``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。
此外，这个函数还接受一个可选参数\ ``resize``\ ，用来将图像大小调整为另一种形状。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-19-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-19-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-19-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-19-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-19-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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"""
        dataset = gluon.data.vision
        trans = [dataset.transforms.ToTensor()]
        if resize:
            trans.insert(0, dataset.transforms.Resize(resize))
        trans = dataset.transforms.Compose(trans)
        mnist_train = dataset.FashionMNIST(train=True).transform_first(trans)
        mnist_test = dataset.FashionMNIST(train=False).transform_first(trans)
        return (gluon.data.DataLoader(mnist_train, batch_size, shuffle=True,
                                      num_workers=get_dataloader_workers()),
                gluon.data.DataLoader(mnist_test, batch_size, shuffle=False,
                                      num_workers=get_dataloader_workers()))



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-19-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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()))



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-19-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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"""
        mnist_train, mnist_test = tf.keras.datasets.fashion_mnist.load_data()
        # 将所有数字除以255，使所有像素值介于0和1之间，在最后添加一个批处理维度，
        # 并将标签转换为int32。
        process = lambda X, y: (tf.expand_dims(X, axis=3) / 255,
                                tf.cast(y, dtype='int32'))
        resize_fn = lambda X, y: (
            tf.image.resize_with_pad(X, resize, resize) if resize else X, y)
        return (
            tf.data.Dataset.from_tensor_slices(process(*mnist_train)).batch(
                batch_size).shuffle(len(mnist_train[0])).map(resize_fn),
            tf.data.Dataset.from_tensor_slices(process(*mnist_test)).batch(
                batch_size).map(resize_fn))



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-19-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    #@save
    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 = paddle.vision.datasets.FashionMNIST(mode="train",
                                                          transform=trans)
        mnist_test = paddle.vision.datasets.FashionMNIST(mode="test",
                                                         transform=trans)
        return (paddle.io.DataLoader(dataset=mnist_train,
                                     batch_size=batch_size,
                                     shuffle=True,
                                     return_list=True,
                                     num_workers=get_dataloader_workers()),
                paddle.io.DataLoader(dataset=mnist_test,
                                     batch_size=batch_size,
                                     return_list=True,
                                     shuffle=True,
                                     num_workers=get_dataloader_workers()))



.. raw:: html

    </div>



.. raw:: html

    </div>

下面，我们通过指定\ ``resize``\ 参数来测试\ ``load_data_fashion_mnist``\ 函数的图像大小调整功能。



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar code"><a href="#mxnet-21-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-21-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-21-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-21-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-21-0">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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


.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (32, 1, 64, 64) <class 'numpy.float32'> (32,) <class 'numpy.int32'>




.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-21-1">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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


.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    torch.Size([32, 1, 64, 64]) torch.float32 torch.Size([32]) torch.int64




.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-21-2">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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


.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    (32, 64, 64, 1) <dtype: 'float32'> (32,) <dtype: 'int32'>




.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-21-3">

.. raw:: latex

   \diilbookstyleinputcell

.. code:: python

    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


.. raw:: latex

   \diilbookstyleoutputcell

.. parsed-literal::
    :class: output

    [32, 1, 64, 64] paddle.float32 [32, 1] paddle.int64




.. raw:: html

    </div>



.. raw:: html

    </div>

我们现在已经准备好使用Fashion-MNIST数据集，便于下面的章节调用来评估各种分类算法。

小结
----

-  Fashion-MNIST是一个服装分类数据集，由10个类别的图像组成。我们将在后续章节中使用此数据集来评估各种分类算法。
-  我们将高度\ :math:`h`\ 像素，宽度\ :math:`w`\ 像素图像的形状记为\ :math:`h \times w`\ 或（\ :math:`h`,\ :math:`w`\ ）。
-  数据迭代器是获得更高性能的关键组件。依靠实现良好的数据迭代器，利用高性能计算来避免减慢训练过程。

练习
----

1. 减少\ ``batch_size``\ （如减少到1）是否会影响读取性能？
2. 数据迭代器的性能非常重要。当前的实现足够快吗？探索各种选择来改进它。
3. 查阅框架的在线API文档。还有哪些其他数据集可用？



.. raw:: html

    <div class="mdl-tabs mdl-js-tabs mdl-js-ripple-effect"><div class="mdl-tabs__tab-bar text"><a href="#mxnet-23-0" onclick="tagClick('mxnet'); return false;" class="mdl-tabs__tab is-active">mxnet</a><a href="#pytorch-23-1" onclick="tagClick('pytorch'); return false;" class="mdl-tabs__tab ">pytorch</a><a href="#tensorflow-23-2" onclick="tagClick('tensorflow'); return false;" class="mdl-tabs__tab ">tensorflow</a><a href="#paddle-23-3" onclick="tagClick('paddle'); return false;" class="mdl-tabs__tab ">paddle</a></div>



.. raw:: html

    <div class="mdl-tabs__panel is-active" id="mxnet-23-0">

`Discussions <https://discuss.d2l.ai/t/1788>`__



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="pytorch-23-1">

`Discussions <https://discuss.d2l.ai/t/1787>`__



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="tensorflow-23-2">

`Discussions <https://discuss.d2l.ai/t/1786>`__



.. raw:: html

    </div>



.. raw:: html

    <div class="mdl-tabs__panel " id="paddle-23-3">

`Discussions <https://discuss.d2l.ai/t/11692>`__



.. raw:: html

    </div>



.. raw:: html

    </div>