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 vote130 views1 answer
Docker remote
Python
1 vote143 views1 answer
Ubuntu cant find python installation
Python
0 vote136 views1 answer
(for in) printing in python
Python
0 vote143 views1 answer
Python Tkinter timer animation
Python
1 vote135 views1 answer
Print(int())
Python
0 vote129 views1 answer
Python mark function as no return
Python
0 vote135 views1 answer
Vreverse all elemetns of a list in place python
Python
15 votes130 views4 answers
Check if float is integer python
Python
4 votes161 views2 answers
Pandas row sum
Python
4 votes173 views5 answers
Module 'datetime' has no attribute 'now' django
Python Django