torchvision.transforms.ToTensor()和torchvision.transforms.Normalize()

最新推荐文章于 2025-04-24 21:30:23 发布

原创

最新推荐文章于 2025-04-24 21:30:23 发布 · 1.1k 阅读

11 ·

CC 4.0 BY-SA版权

文章标签：

#torchvision #ToTensor #Normalize

本文详细解析了PyTorch中`torchvision.transforms`模块的`ToTensor()`和`Normalize()`函数。`ToTensor()`将图像像素值从[0,255]缩放到[0,1]；`Normalize()`进一步将值域变换到[-1,1]，通过指定的均值和标准差进行归一化。这两个转换常用于预处理图像数据，以便于输入到深度学习模型中。对于不同通道数的图像，如RGB或灰度图，`Normalize()`的参数设置也有所不同。

import torchvision.transforms as transform
transform.ToTensor()
transform.Normalize((0.5, 0.5, 0.5),(0.5, 0.5, 0.5))

torchvision.transforms.ToTensor()

一般读入图像像素值值域范围为[0, 255]，ToTensor()能够把范围从[0, 255]变换到[0, 1]。
在这里插入图片描述

class ToTensor(object):
    """Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor.

    Converts a PIL Image or numpy.ndarray (H x W x C) in the range
    [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0]
    if the PIL Image belongs to one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1)
    or if the numpy.ndarray has dtype = np.uint8

    In the other cases, tensors are returned without scaling.
    """

    def __call__(self, pic):
        """
        Args:
            pic (PIL Image or numpy.ndarray): Image to be converted to tensor.

        Returns:
            Tensor: Converted image.
        """
        return F.to_tensor(pic)

    def __repr__(self):
        return self.__class__.__name__ + '()'