How to calculate the parameters in torchvision.transforms.Normalize(mean, std)

[xiexu666]

I have load my own image dataset , but don't know how to calculate the mean and std
train_data=torchvision.datasets.ImageFolder('F:/trainData',transform=transforms.Compose( [ transforms.Scale(256), transforms.RandomCrop(224), transforms.ToTensor() ]))

[xiexu666]

I find the result in http://forums.fast.ai/t/image-normalization-in-pytorch/7534/7

[soumith]

you can simply run some of the dataset you have through computing mean and standard deviation.