torchvison源码剖析【1】transform.ToTensor()

最新推荐文章于 2025-03-08 16:30:30 发布

原创

最新推荐文章于 2025-03-08 16:30:30 发布 · 4.1k 阅读

2 ·

CC 4.0 BY-SA版权

PIL转tensor:

def pil2tensor():
    img=Image.open(img_path)
    totensor=torchvision.transforms.ToTensor()
    #torchvision.transforms.ToTensor()函数自动转格式
    img=totensor(img)
    img=img.cpu()
    print(img.size())# torch.Size([3, 300, 533])
    print(img.dtype)# torch.float32
    print(type(img))# <class 'torch.Tensor'>
pil2tensor()

源码:

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].
    """

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

        Returns:
            Tensor: Converted image.
        """