EiZSSKJr SSKJrJrJr SSKrSSKJr SSK J r "SS\ 5r g) ) annotations)AnyMappingSequenceN) tree_flatten)TVTensorc\rSrSr%SrS\S'\SS.SSjj5rSSSS .SS jjr\SSS jj5r SS .SSjjr S r g) KeyPoints u:class:`torch.Tensor` subclass for tensors with shape ``[..., 2]`` that represent points in an image. .. note:: Support for keypoints was released in TorchVision 0.23 and is currently a BETA feature. We don't expect the API to change, but there may be some rare edge-cases. If you find any issues, please report them on our bug tracker: https://github.com/pytorch/vision/issues?q=is:open+is:issue Each point is represented by its X and Y coordinates along the width and height dimensions, respectively. Each point is represented by its X and Y coordinates along the width and height dimensions, respectively. KeyPoints may represent any object that can be represented by sequences of 2D points: - `Polygonal chains `_, including polylines, Bézier curves, etc., which can be of shape ``[N_chains, N_points, 2]``. - Polygons, which can be of shape ``[N_polygons, N_points, 2]``. - Skeletons, which can be of shape ``[N_skeletons, N_bones, 2, 2]`` for pose-estimation models. .. note:: Like for :class:`torchvision.tv_tensors.BoundingBoxes`, there should only be a single instance of the :class:`torchvision.tv_tensors.KeyPoints` class per sample e.g. ``{"img": img, "poins_of_interest": KeyPoints(...)}``, although one :class:`torchvision.tv_tensors.KeyPoints` object can contain multiple key points Args: data: Any data that can be turned into a tensor with :func:`torch.as_tensor`. canvas_size (two-tuple of ints): Height and width of the corresponding image or video. dtype (torch.dtype, optional): Desired data type of the bounding box. If omitted, will be inferred from ``data``. device (torch.device, optional): Desired device of the bounding box. If omitted and ``data`` is a :class:`torch.Tensor`, the device is taken from it. Otherwise, the bounding box is constructed on the CPU. requires_grad (bool, optional): Whether autograd should record operations on the bounding box. If omitted and ``data`` is a :class:`torch.Tensor`, the value is taken from it. Otherwise, defaults to ``False``. tuple[int, int] canvas_sizeT) check_dimscU(aMURS:XaURS5nO+URSS:wa[SUR35eUR U5nX$lU$)Nrrz)Expected a tensor of shape (..., 2), not )ndim unsqueezeshape ValueError as_subclassr)clstensorrrpointss ^/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/tv_tensors/_keypoints.py_wrapKeyPoints._wrap;sd {{a))!,b!Q& #LV\\N![\\##C(( Ndtypedevice requires_gradc@URXXES9nURXbS9$)Nrr) _to_tensorr)rdatarr r!r"rs r__new__KeyPoints.__new__Fs'&^yyy99rc^[X#(a[UR55OS-5upE[SU55nURm[ U[ R5(a,[ U[5(d[RUTSS9nU$[ U[[45(a[U5"U4SjU55nU$)Nr)c3T# UHn[U[5(dMUv M g7f)N) isinstancer ).0xs r )KeyPoints._wrap_output..[s(\Kq:aQZC[Ks( (Frrc3N># UHn[RUTSS9v M g7f)Fr1N)r r)r-partrs rr/r0bs$!vougk)//$K\a/"bous"%) rtuplevaluesnextrr,torchTensorr rlisttype)routputargskwargs flat_params_first_keypoints_from_argsrs @r _wrap_outputKeyPoints._wrap_outputRs&deFMMO.DTV&WX $((\K(\$\!/;; fell + +Jvy4Q4Q__VQV_WF  . .&\!vou!vvF r)tensor_contentsc4URURS9$)Nr$) _make_reprr)selfrCs r__repr__KeyPoints.__repr__es4+;+;<rYs%")) , [=[=r