pytorch中如何实现逆归一化

哼律

于 2021-03-18 09:29:31 发布

阅读量2.6k

点赞数 3

分类专栏： Pytorch 深度学习文章标签： pytorch

本文链接：https://blog.csdn.net/qq_38327769/article/details/114963206

版权

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 ]),