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 vote139 views1 answer
How to preserve white space when joining an array python
Python
0 vote107 views1 answer
Logartim normalization python pandas
Python
0 vote114 views1 answer
Jaccard distance python
Python
0 vote119 views1 answer
Python compactar arquivo antes de exportar
Python
22 votes112 views5 answers
Select rows with nan pandas
Python
0 vote123 views1 answer
Remove percentage in python
Python
17 votes132 views2 answers
Import "rest_framework.views" could not be resolved
Python
23 votes172 views2 answers
Python search list
Python
5 votes169 views1 answer
Pandas version check in python
Python
73 votes117 views6 answers
Remove duplicates python
Python