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

7 votes166 views4 answers
Jupyter notebook plot larger
Python
0 vote167 views1 answer
2sf python
Python
0 vote168 views1 answer
Build mac app from python script
Python
21 votes127 views16 answers
How to convert pandas price column to integer
Python
4 votes171 views2 answers
Python replace by dictionary
Python
0 vote170 views5 answers
Generator expressions python
Python
0 vote158 views1 answer
Python sort list by rule
Python
0 vote198 views1 answer
Pdfs in django
Python Django
2 votes178 views1 answer
Django queryset get all distinct
Python Django
4 votes178 views2 answers
Python join array of ints
Python