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 vote176 views2 answers
Python defualt error handler
Python
0 vote195 views1 answer
Spacy text annotation dict comprehension
Python
2 votes175 views1 answer
How to append element python
Python
1 vote192 views2 answers
Permutation of a string in python
Python
4 votes178 views2 answers
Uuid regex
Python
9 votes181 views6 answers
Reaction role discord.py
Python
21 votes168 views5 answers
Python exception
Python
1 vote194 views5 answers
Transpose matrix python
Python
0 vote205 views1 answer
Django array of dates
Python Django
0 vote205 views1 answer
Get month day year 12 hour time format python
Python