10分钟
读取和归一化 CIFAR10
In [ ]:
%matplotlib inline使用torchvision可以非常容易地加载CIFAR10。
In [1]:
import torch
import torchvision
import torchvision.transforms as transformstorchvision的输出是[0,1]的PILImage图像，我们把它转换为归一化范围为[-1, 1]的张量。
In [2]:
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data\cifar-10-python.tar.gz
100%|███████████████████████████████████████████████████████████████████████████████▉| 170M/170M [20:39<00:00, 155kB/s]Files already downloaded and verified
我们展示一些训练图像。
In [3]:
import matplotlib.pyplot as plt
import numpy as np
# 展示图像的函数
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
# 获取随机数据
dataiter = iter(trainloader)
images, labels = dataiter.next()
# 展示图像
imshow(torchvision.utils.make_grid(images))
# 显示图像标签
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))171MB [20:51, 155kB/s] cat car cat ship
学员评价