Eiy SSKJr SSKrSSKrSSKJrJr SSKJr SSKJ r SSK J r SSK J r S S KJrJr \R"R$SS \S \\\\4S \\S\S\4 Sjj5r"SS\R.5rg))UnionN)nnTensor)BroadcastingList2)_pair)_assert_has_ops)_log_api_usage_once)check_roi_boxes_shapeconvert_boxes_to_roi_formatinputboxes output_size spatial_scalereturnc[RR5(d2[RR5(d[ [ 5 [ 5 [U5 Un[U5n[U[R5(d [U5n[RRR XX2SUS5upVU$)a Performs Region of Interest (RoI) Pool operator described in Fast R-CNN Args: input (Tensor[N, C, H, W]): The input tensor, i.e. a batch with ``N`` elements. Each element contains ``C`` feature maps of dimensions ``H x W``. boxes (Tensor[K, 5] or List[Tensor[L, 4]]): the box coordinates in (x1, y1, x2, y2) format where the regions will be taken from. The coordinate must satisfy ``0 <= x1 < x2`` and ``0 <= y1 < y2``. If a single Tensor is passed, then the first column should contain the index of the corresponding element in the batch, i.e. a number in ``[0, N - 1]``. If a list of Tensors is passed, then each Tensor will correspond to the boxes for an element i in the batch. output_size (int or Tuple[int, int]): the size of the output after the cropping is performed, as (height, width) spatial_scale (float): a scaling factor that maps the box coordinates to the input coordinates. For example, if your boxes are defined on the scale of a 224x224 image and your input is a 112x112 feature map (resulting from a 0.5x scaling of the original image), you'll want to set this to 0.5. Default: 1.0 Returns: Tensor[K, C, output_size[0], output_size[1]]: The pooled RoIs. rr )torchjit is_scripting is_tracingr roi_poolrr r isinstancerr ops torchvision)rrrrroisoutput_s U/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/ops/roi_pool.pyrrs< 99 ! ! # #EII,@,@,B,BH%% D $K dELL ) )*40 %%..uMWX>[fgh[ijIF Mcr^\rSrSrSrS\\S\4U4SjjrS\ S\ \ \ \ 4S\ 4S jr S\ 4S jrS rU=r$) RoIPool8z See :func:`roi_pool`. rrcP>[TU]5 [U5 XlX lgN)super__init__r rr)selfrr __class__s rr'RoIPool.__init__=s" D!&*r rrrcD[XURUR5$r%)rrr)r(rrs rforwardRoIPool.forwardCsT%5%5t7I7IJJr clURRSURSURS3nU$)Nz (output_size=z, spatial_scale=))r)__name__rr)r(ss r__repr__RoIPool.__repr__Fs;~~&&'}T5E5E4FFVW[WiWiVjjk lr )rr)r0 __module__ __qualname____firstlineno____doc__rintfloatr'rrlistr,strr2__static_attributes__ __classcell__)r)s@rr"r"8s^+$5c$:+5+ KVK5f1E+FK6K#r r")g?)typingrrtorch.fxrrtorch.jit.annotationsrtorch.nn.modules.utilsrtorchvision.extensionrutilsr _utilsr r fxwrapr:r8r9rModuler"r rrIs 3(1'F  & & f% &&#3'& &  &&Rbiir