torchvision.transforms.ToTensor（细节）对应caffe的转换

目录

1）torchvision.transforms.ToTensor

2）pytorch的图像预处理和caffe中的图像预处理 

---

写这篇文章的初衷，就是同事跑过来问我，pytorch对图像的预处理为什么和caffe的预处理存在差距，我也是第一次注意到这个问题；

1）torchvision.transforms.ToTensor

直接贴代码：

第一段代码：

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.
        """
        return F.to_tensor(pic)

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

第二段代码： 

def to_tensor(pic):
    """Convert a ``PIL