1.引用包

import numpy as np
import torch
import torchvision
from torch.utils import data
from torchvision import transforms#数据操作
import random
import matplotlib.pyplot as plt
import matplotlib
from torch.utils import data
from torch import nn
import d2l
import warnings

2.下载并获取图片数据集FashionMnist

arnings.filterwarnings('ignore')
trans = transforms.ToTensor() #把图片转成预处理，转成张量
mnist_train = torchvision.datasets.FashionMNIST(
    root="D:\PycharmDocument\limu\data", train=True, transform=trans, download=True)
mnist_test = torchvision.datasets.FashionMNIST(
    root="D:\PycharmDocument\limu\data", train=False, transform=trans, download=True)

获取图标y（简化形式）

def get_fashion_mnist_labels(labels):
    text_labels=['t-shirt', 'trouser', 'pullover', 'dress', 'coat','sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
    return text_labels[int(labels)]

图片显示（自制）

X,y=next(iter(data.DataLoader(mnist_train,batch_size=18)))
def show_image(X,y,num_rows,num_cols,scale=1.5):
    figsize=[num_cols*scale,num_rows*scale]#画布大小
    fig,axes=plt.subplots(num_rows,num_cols,figsize=figsize) #设置画布和子图
    ax = axes.flatten() #对图片进行平展
    for i in range(num_rows*num_cols):
        ax[i].imshow(X[i].squeeze().numpy())  # 对第一个字图，展示第一个图片
        ax[i].set(title=get_fashion_mnist_labels(y[i].item())) #对第一个字图设置标题
        ax[i].set_xticks([])#清空x轴
        ax[i].set_yticks([])#清空x轴
    plt.tight_layout()#自动调整子图间距
    plt.show()展示

图片显示（李沐）

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  """绘制图像列表"""
    figsize = (num_cols * scale, num_rows * scale)#画布大小
    _, axes = d2l.plt.subplots(num_rows, num_cols, figsize=figsize)#画布和子图大小
    axes = axes.flatten()#子图平展
    for i, (ax, img) in enumerate(zip(axes, imgs)): #对子图和图对应起来，并依次取出
        if torch.is_tensor(img):
            # 图片张量
            ax.imshow(img.numpy()) #如果是张量，以numpy形式展示
        else:
            # PIL图片
            ax.imshow(img)
        ax.axes.get_xaxis().set_visible(False) #去除x轴
        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));