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

3 votes259 views1 answer
Discord python webhook
Python
-1 vote285 views1 answer
Loading .dat file in python
Python
15 votes294 views5 answers
Pandas profiling
Python
1 vote276 views1 answer
Select rows from a DataFrame based on column values?
Python
11 votes300 views2 answers
Adding to python path
Python
2 votes260 views1 answer
Standardize columns in pandas
Python
0 vote310 views1 answer
Flask gunicorn get ip
Python Flask
1 vote277 views1 answer
How to input 2-d array in python
Python
10 votes288 views1 answer
Create dataframe with column names pandas
Python
4 votes293 views2 answers
Python get appdata path
Python