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 vote325 views1 answer
Pycairo
Python
0 vote356 views1 answer
Pandas recognize type from strings
Python
2 votes332 views1 answer
Save a dict to pickle
Python
-1 vote304 views2 answers
Python how to add 2 numbers
Python
0 vote895 views1 answer
Audioplayer python
Python
0 vote316 views1 answer
Check check writability of the file
Python
4 votes324 views1 answer
Numpy mean 2 arrays
Python
-1 vote314 views1 answer
How to convert pandas series to 2d numpy array
Python
2 votes329 views2 answers
Python dataframe get numeric columns
Python
11 votes313 views3 answers
Python random choice int
Python