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 votes325 views1 answer
Split array into chunks python
Python
0 vote382 views1 answer
Set allowed methods flask
Python
0 vote313 views1 answer
How to get a row of a dataframe with subset columns in python
Python
3 votes362 views1 answer
Remove keys from dict python
Python
0 vote408 views1 answer
Plt text verticalalignment
Python
6 votes332 views5 answers
Bar plot matplotlib
Python
0 vote316 views1 answer
Python returning rows and columns from a matrix string
Python
26 votes307 views4 answers
Python send email with attachment
Python
2 votes316 views1 answer
Save df to txt
Python
114 votes327 views6 answers
Python pip install
Python