0.5 值只是近似值cifar10三个通道(r、g、b)的平均值和标准值。 cifar10 训练集的精确值为
- mean:
0.49139968, 0.48215827 ,0.44653124
- std:
0.24703233 0.24348505 0.26158768
您可以使用以下脚本计算这些:
import torch
import numpy
import torchvision.datasets as datasets
from torchvision import transforms
cifar_trainset = datasets.CIFAR10(root='./data', train=True, download=True, transform=transforms.ToTensor())
imgs = [item[0] for item in cifar_trainset] # item[0] and item[1] are image and its label
imgs = torch.stack(imgs, dim=0).numpy()
# calculate mean over each channel (r,g,b)
mean_r = imgs[:,0,:,:].mean()
mean_g = imgs[:,1,:,:].mean()
mean_b = imgs[:,2,:,:].mean()
print(mean_r,mean_g,mean_b)
# calculate std over each channel (r,g,b)
std_r = imgs[:,0,:,:].std()
std_g = imgs[:,1,:,:].std()
std_b = imgs[:,2,:,:].std()
print(std_r,std_g,std_b)
此外,您可能会发现相同的平均值和标准值here https://github.com/tomgoldstein/loss-landscape/blob/64ef4d57f8dabe79b57a637819c44e48eda98f33/cifar10/dataloader.py#L15 and here https://gist.github.com/weiaicunzai/e623931921efefd4c331622c344d8151#gistcomment-2851662