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 vote95 views1 answer
R how to merge data frames
Python
1 vote97 views1 answer
Accuracy score sklearn syntax
Python
3 votes97 views1 answer
Py change background
Python
62 votes95 views5 answers
How to pick a random number in a list python
Python
0 vote95 views1 answer
Counting combinations python
Python
11 votes113 views6 answers
Enumerate python
Python
15 votes87 views2 answers
Python make api request
Python
4 votes103 views1 answer
Python network programming
Python
4 votes103 views2 answers
Python code to open windows command prompt
Python
0 vote97 views1 answer
Numeric up down python tkinter
Python