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

2 votes142 views1 answer
How to make a letter animation in python
Python
0 vote134 views1 answer
Stores number in set using input in python
Python
0 vote148 views1 answer
Compare two data frames in assert
Python
0 vote150 views1 answer
Django jinja else if template tags
Python
0 vote150 views1 answer
Random ordered slice of an array
Python
0 vote138 views1 answer
Save jupyter notebook session
Python
0 vote181 views1 answer
Django command to fetch all columns of a table
Python Django
0 vote149 views1 answer
Mechanize python LE #3
Python
1 vote158 views1 answer
Adding variable in python
Python
0 vote172 views1 answer
Python redirect with button click
Python