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

4 votes110 views5 answers
Print hello in python
Python
0 vote110 views1 answer
How to make a column a factor in pandas
Python
1 vote99 views1 answer
What is the meaning of illiteral with base 10
Python
1 vote105 views1 answer
Discord get bot profile picture
Python
0 vote110 views1 answer
Kivy button on press call function with arguments
Python
0 vote105 views10 answers
Installez django-cruds-adminlte
Python
1 vote188 views1 answer
Flask clear session
Python Flask
0 vote61 views3 answers
Django messages
Python
17 votes102 views4 answers
Get ip address python
Python
0 vote99 views2 answers
Pandas groupby aggregate quantile
Python