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 vote240 views1 answer
How to take long input in python
Python
0 vote264 views1 answer
RemoveStopWords
Python
0 vote262 views1 answer
Hex string to hex number
Python
9 votes243 views6 answers
Python dictionary
Python
1 vote266 views1 answer
Get list of objects in group godot
Python
0 vote257 views1 answer
Iterating over the two ranges simultaneously and saving it in database
Python
0 vote230 views1 answer
In np array how to make element as 1 if it exceeds the threshold
Python
0 vote255 views1 answer
Python subprocess print stdout while process running
Python
19 votes258 views2 answers
Set background colour tkinter
Python
3 votes261 views1 answer
For each digit in number python
Python