09 图片分类数据集
colab中如果绘图步骤报错的话可能是matplotlib包版本低的原因,可以运行!pip install --upgrade matplotlib更新一下。
%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()
#用于在数字标签索引及其文本名称之间进行转换。
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]
#scale可以调节图片的大小,num_rows指有几行,num_cols指有几列
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
def get_dataloader_workers():
"""使用4个进程来读取数据"""
return 4
#最后将全部的函数集合起来
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)) #需要的话可以修改图片大小
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()))
# 通过ToTensor实例将图像数据从PIL类型变成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() #生成转换成tensor的转换器
#root为预下载好的数据集的路径,train=True代表为训练集数据,download=True表示默认下载
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)
batch_size = 256
#shuffle = True表示要随机打乱
train_iter = data.DataLoader(mnist_train, batch_size, shuffle=True,
num_workers=get_dataloader_workers())
#最后调用函数即可得到读取好的训练和测试数据集
train_iter, test_iter = load_data_fashion_mnist(256, resize=48)
for X, y in train_iter:
print(X.shape, X.dtype, y.shape, y.dtype)
break
图片与标签输出:
不同进程数读取数据的时间对比:
测试resize与正常读取功能: