The mean and std are not for each tensor, but from the whole dataset. What you are trying to do doesn't really matter, you just want a scale ... ... <看更多>

"""Normalize a float tensor image with mean and standard deviation. This transform does not support PIL Image. .. note:: This transform acts out of place by ... ... <看更多>

The normalisation you do does not re-scale to [0,1] range! It normalises to have mean 0 and std 1 instead. To scale the tensor to be in [0 ... ... <看更多>

import torchvision.transforms as transforms transform = transforms.Compose( [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), ... ... <看更多>