\hNSSKJr SSKJr SSKrSSKrSSKJr "SS\5r g)) annotations)AnyN)TVTensorcR\rSrSrSrSSSS.S SjjrSS.S SjjrSrg) Image a:class:`torch.Tensor` subclass for images with shape ``[..., C, H, W]``. .. note:: In the :ref:`transforms `, ``Image`` instances are largely interchangeable with pure :class:`torch.Tensor`. See :ref:`this note ` for more details. Args: data (tensor-like, PIL.Image.Image): Any data that can be turned into a tensor with :func:`torch.as_tensor` as well as PIL images. dtype (torch.dtype, optional): Desired data type. If omitted, will be inferred from ``data``. device (torch.device, optional): Desired device. If omitted and ``data`` is a :class:`torch.Tensor`, the device is taken from it. Otherwise, the image is constructed on the CPU. requires_grad (bool, optional): Whether autograd should record operations. If omitted and ``data`` is a :class:`torch.Tensor`, the value is taken from it. Otherwise, defaults to ``False``. Ndtypedevice requires_gradcX[U[RR5(aSSKJn UR U5nUR XX4S9nURS:a[SURS35eURS:XaURS5nURU5$)Nr) functionalr z!Tensor must be 2D or higher, got z D tensor.) isinstancePILrtorchvision.transforms.v2r pil_to_tensor _to_tensorndim ValueError unsqueeze as_subclass)clsdatar r r Ftensors W/var/www/fran/franai/venv/lib/python3.13/site-packages/torchvision/tv_tensors/_image.py__new__ Image.__new__s dCIIOO , , A??4(D&^ ;;?@ YWX X [[A %%a(F!!#&&)tensor_contentsc"UR5$)N) _make_repr)selfr"s r__repr__Image.__repr__4s  r!) rrr ztorch.dtype | Noner ztorch.device | str | int | Noner z bool | Nonereturnr)r"rr)str)__name__ __module__ __qualname____firstlineno____doc__rr&__static_attributes__r(r!rrr sV.%)26%) ''" ' 0 ' # ' '*26!!r!r) __future__rtypingr PIL.Imagertorch _tv_tensorrrr(r!rr6s " *!H*!r!