Torchvision.transforms

from torchvision import transforms as transforms
transform = transforms.Compose([
    transforms.RandomCrop(32, padding=4),  #先四周填充0，在把图像随机裁剪成32*32
    transforms.RandomHorizontalFlip(),  #图像一半的概率翻转，一半的概率不翻转
    transforms.RandomRotation((-45,45)), #随机旋转
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.229, 0.224, 0.225)), #R,G,B每层的归一化用到的均值和方差
])

Source: pytorch-tutorial.readthedocs.io

Similar codes

0 vote198 views1 answer
Python random phone number
Python
0 vote193 views1 answer
Python numpy find nearest value
Python
0 vote188 views1 answer
Python get packages path
Python
8 votes200 views2 answers
Pandas filter rows by value in list
Python
2 votes329 views2 answers
Pandas series to string without index
Python
0 vote202 views1 answer
Python split string after substring
Python
2 votes165 views1 answer
Remove , from list python
Python
0 vote204 views1 answer
Add_node python
Python
2 votes188 views1 answer
Copy website
Python
8 votes226 views6 answers
Fizzbuzz python solution
Python