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 vote159 views1 answer
Pyqt graph
Python
5 votes143 views1 answer
Mutable and immutable in python
Python
0 vote133 views1 answer
Python default parameters depend on other paramters
Python
0 vote139 views1 answer
File = Root() path = file.fileDialog() print("PATH = ", path)
Python
0 vote148 views1 answer
Pylatex add package
Python
1 vote166 views1 answer
Python clamp
Python
1 vote143 views1 answer
Distribution plot with curve python
Python
-1 vote178 views2 answers
Convert two numpy array to pandas dataframe
Python
0 vote136 views1 answer
Html.unescape python
Python
1 vote168 views1 answer
Get active window title python
Python