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 votes238 views2 answers
How to select a single cell in a pandas dataframe
Python
4 votes183 views1 answer
Django listview
Python Django
0 vote235 views2 answers
Split pdf in python
Python
0 vote263 views1 answer
From a list of lists - find all length of list
Python
0 vote226 views1 answer
Python struct pack
Python
0 vote235 views1 answer
How to colour letters in python
Python
0 vote239 views1 answer
How to train Longistic regression with given threshold
Python
1 vote249 views1 answer
Reading the data
Python
27 votes245 views6 answers
Remove column from dataframe
Python
5 votes236 views3 answers
Python calculate prime numbers until numer
Python