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

1 vote187 views1 answer
Remove all pyc
Python
2 votes172 views1 answer
Add list to end of list python
Python
0 vote171 views1 answer
Pandas astype str still object
Python
76 votes236 views6 answers
Python main
Python
76 votes240 views6 answers
Select a random element from a list python
Python
2 votes189 views3 answers
Django queryset to list
Python
1 vote247 views1 answer
Get most repeated instance in a queryset django
Python Django
-1 vote209 views1 answer
Python one sample t-test
Python
-1 vote185 views1 answer
Pyaudio mic stream
Python
1 vote182 views1 answer
How to use get-pip.py
Python