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 vote299 views1 answer
Programação funcional python - append
Python
0 vote320 views1 answer
How to get a list of all values in a column df
Python
1 vote361 views1 answer
Django get part of queryset
Python Django
0 vote292 views1 answer
Programe to find contagious sum of sequence
Python
35 votes290 views6 answers
Install matplotlib
Python
-1 vote319 views1 answer
Count variable in class python
Python
1 vote285 views1 answer
Django foreign key error Cannot assign must be a instance
Python
0 vote297 views1 answer
How to solve trig equations with jupyter notebook
Python
9 votes322 views1 answer
Sleep in python 3
Python
16 votes254 views8 answers
Curl in python
Python