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 votes221 views4 answers
Create dict from two columns pandas
Python
6 votes246 views4 answers
Pandas read csv without header
Python
0 vote210 views1 answer
Python update flask
Python
1 vote219 views1 answer
.pyc
Python
0 vote246 views2 answers
Access column pandas
Python
-2 votes203 views1 answer
Python multiplayer
Python
1 vote241 views2 answers
Selenium text value is empty in flask returns
Python Flask
0 vote219 views1 answer
Python [:-1]
Python
0 vote203 views1 answer
Python get names of input arguments
Python
0 vote252 views3 answers
How to find a word in list python
Python