Normalize的使用————Transforms

哔哩大学的PyTorch深度学习快速入门教程（绝对通俗易懂！）【小土堆】
的P12讲讲述了transforms中Normalize（归一化）的使用。

Normalize

Normalize的注释：

class Normalize(torch.nn.Module):
    """Normalize a tensor image with mean and standard deviation.
    This transform does not support PIL Image.
    用均值和标准差对张量图像进行归一化。这个变换不支持PIL Image。
    Given mean: ``(mean[1],...,mean[n])`` and std: ``(std[1],..,std[n])`` for ``n``
    channels, this transform will normalize each channel of the input
    ``torch.*Tensor`` i.e.,
    ``output[channel] = (input[channel] - mean[channel]) / std[channel]``

    .. note::
        This transform acts out of place, i.e., it does not mutate the input tensor.

    Args:
        mean (sequence): Sequence of means for each channel.
        std (sequence): Sequence of standard deviations for each channel.
        inplace(bool,optional): Bool to make this operation in-place.

    """

    def __init__(self, mean, std, inplace=False):
        super().__init__()
        self.mean = mean
        self.std = std
        self.inplace = inplace

    def forward(self, tensor: Tensor) -> Tensor:
        """
        Args:
            tensor (Tensor): Tensor image to be normalized.

        Returns:
            Tensor: Normalized Tensor image.
        """
        return F.normalize(tensor, self.mean, self.std, self.inplace)

    def __repr__(self):
        return self.__class__.__name__ + '(mean={0}, std={1})'.format(self.mean, self.std)

接上一个的代码后面加上：

trans_norm = transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
#需要输入均值和标准差，因为我们的图片不是rgb三层的，提供三声道标准差
img_norm = trans_norm(img_tensor)
#上边做好的image的tensor数据类型
#output[channel] = (input[channel] - mean[channel]) / std[channel]
print(img_norm[0][0][0])
writer.add_image("Normalize",img_norm)
writer.close()

运行结果为：

经过归一化后的图片（上边为归一化后，下边为原图）：