pytorch中如何实现逆归一化

1. 第一种方法，创一个类，再进行调用

class UnNormalize(object):
    def __init__(self, mean, std):
        self.mean = mean
        self.std = std

    def __call__(self, tensor):
        """
        Args:
            tensor (Tensor): Tensor image of size (C, H, W) to be normalized.
        Returns:
            Tensor: Normalized image.
        """
        for t, m, s in zip(tensor, self.mean, self.std):
            t.mul_(s).add_(m)
            # The normalize code -> t.sub_(m).div_(s)
        return tensor

然后调用这个类

unorm = UnNormalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
unorm(tensor)

2 . 第二种方法，直接了当，清楚明白

• 两次transform

un_norm = transforms.Compose([ transforms.Normalize(mean = [ 0., 0., 0. ],
                                                     std = [ 1/0.229, 1/0.224, 1/0.225 ]),
                                transforms.Normalize(mean = [ -0.485, -0.456, -0.406 ],
                                                     std = [ 1., 1., 1. ]),
                               ])

inv_tensor = un_norm(inp_tensor)

• 一次transform

un_norm = transforms.Normalize(
    mean=[-0.485/0.229, -0.456/0.224, -0.406/0.225],
    std=[1/0.229, 1/0.224, 1/0.225]
)
inv_tensor = un_norm(tensor)