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

2 votes309 views1 answer
Downgrade python 3.8 to 3.7 ubuntu
Python
0 vote304 views1 answer
Data exfiltration icmp
Python
2 votes307 views3 answers
Building a fibbanaci sequence in python
Python
-2 votes276 views1 answer
Python multiplayer
Python
5 votes324 views4 answers
How to capture cmd output in python
Python
7 votes284 views1 answer
Python xrange
Python
1 vote272 views1 answer
Numpy computer false positive and false negative
Python
0 vote293 views1 answer
Python reading into a text file and diplaying items in a user friendly manner
Python
0 vote332 views2 answers
Python merge strings
Python
16 votes326 views3 answers
Nan vs nat pandas
Python