[人工智能]PIL转tensor 以及 Torch.new()方法使用记录

from PIL import Image
import matplotlib.pyplot as plt
img_b = Image.new("RGB",(32,32))
plt.imshow(img_b)
plt.show()

PIL转tensor方法：

1. 先转numpy，再用torch.from_numpy（）；

img_b_tensor = torch.from_numpy(np.asarray(img_b))
img_b_tensor.size()
Out[36]: torch.Size([32, 32, 3])

2. 使用torchvision.transforms

transs = transforms.ToTensor()
img_b_tensor_two = transs(img_b)
img_b_tensor_two.size()
Out[37]: torch.Size([3, 32, 32])

注意：
3. ToTensor()函数会制动将图像size变为chw；
4. 查看ToTensor()函数可知，其思路也是转换成numpy。只不过ToTensor中加入了除以255的步骤，对图像进行了归一化。

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__ + '()'

def to_tensor(pic):
    """Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor.

    See ``ToTensor`` for more details.

    Args:
        pic (PIL Image or numpy.ndarray): Image to be converted to tensor.

    Returns:
        Tensor: Converted image.
    """
    if not(_is_pil_image(pic) or _is_numpy_image(pic)):
        raise TypeError('pic should be PIL Image or ndarray. Got {}'.format(type(pic)))

    if isinstance(pic, np.ndarray):
        # handle numpy array
        img = torch.from_numpy(pic.transpose((2, 0, 1)))
        # backward compatibility
        if isinstance(img, torch.ByteTensor):
            return img.float().div(255)
        else:
            return img

    if accimage is not None and isinstance(pic, accimage.Image):
        nppic = np.zeros([pic.channels, pic.height, pic.width], dtype=np.float32)
        pic.copyto(nppic)
        return torch.from_numpy(nppic)

    # handle PIL Image
    if pic.mode == 'I':
        img = torch.from_numpy(np.array(pic, np.int32, copy=False))
    elif pic.mode == 'I;16':
        img = torch.from_numpy(np.array(pic, np.int16, copy=False))
    elif pic.mode == 'F':
        img = torch.from_numpy(np.array(pic, np.float32, copy=False))
    elif pic.mode == '1':
        img = 255 * torch.from_numpy(np.array(pic, np.uint8, copy=False))
    else:
        img = torch.ByteTensor(torch.ByteStorage.from_buffer(pic.tobytes()))
    # PIL image mode: L, P, I, F, RGB, YCbCr, RGBA, CMYK
    if pic.mode == 'YCbCr':
        nchannel = 3
    elif pic.mode == 'I;16':
        nchannel = 1
    else:
        nchannel = len(pic.mode)
    img = img.view(pic.size[1], pic.size[0], nchannel)
    # put it from HWC to CHW format
    # yikes, this transpose takes 80% of the loading time/CPU
    img = img.transpose(0, 1).transpose(0, 2).contiguous()
    if isinstance(img, torch.ByteTensor):
        return img.float().div(255)
    else:
        return img

Torch.new()方法用于创建一个新的Tensor，该Tensor的type和device都和原有Tensor一致，且无内容：

tensor_one = img_b_tensor.new(*(5,32,32))

tensor_two = img_b_tensor.new((5,32,32,3))

tensor_one = img_b_tensor.new(*(5,32,32,3))

tensor_two.size()
Out[43]: torch.Size([4])

tensor_one.size()
Out[44]: torch.Size([5, 32, 32, 3])

tensor_three = img_b_tensor.new()

tensor_three.size()
Out[46]: torch.Size([0])

这在使用的时候，需要加入size参数，注意*(参数)与（参数）导致的新建tensor的size区别
(参数)：返回tensor维度是len((维度))
*(参数)：返回tensor维度是(参数)
无size参数则为空