+ j)^RIt^RIt^RIHtHt^RIHt^RIHt^RIH t ^RI H t H t ]PPR RRll4t!R R ]P 4tR#) N)nnTensor)_pair)_assert_has_ops)_log_api_usage_once)check_roi_boxes_shapeconvert_boxes_to_roi_formatc `V^8dQhR\R\R\R\R\R\/#)inputboxes output_size spatial_scalesampling_ratioreturn)rintfloat)formats"]/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/ops/ps_roi_align.py __annotate__r sD// / // /  /  /c\PP4'g4\PP4'g\ \ 4\ 4\V4Tp\V4p\V\P4'g \V4p\PPP WW2^,V^,V4wrgV#)a Performs Position-Sensitive Region of Interest (RoI) Align operator mentioned in Light-Head 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 (in bins or pixels) after the pooling 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 sampling_ratio (int): number of sampling points in the interpolation grid used to compute the output value of each pooled output bin. If > 0, then exactly ``sampling_ratio x sampling_ratio`` sampling points per bin are used. If <= 0, then an adaptive number of grid points are used (computed as ``ceil(roi_width / output_width)``, and likewise for height). Default: -1 Returns: Tensor[K, C / (output_size[0] * output_size[1]), output_size[0], output_size[1]]: The pooled RoIs )torchjit is_scripting is_tracingr ps_roi_alignrrr isinstancerr ops torchvision)r r rrrroisoutput_s&&&&& rrr sJ 99 ! ! # #EII,@,@,B,BL)% D $K dELL ) )*40 %%22 ]NKNNIF Mrcfaa]tRt^>toRtV3RlV3RlltV3RlRltV3RlRltRtVt V;t #) PSRoIAlignz See :func:`ps_roi_align`. c,<V^8dQhRS[RS[RS[/#)r rrr)rr)r __classdict__s"rrPSRoIAlign.__annotate__Cs) - - - - -rc^<\SV`4\V4WnW nW0nR#N)super__init__rrrr)selfrrr __class__s&&&&rr,PSRoIAlign.__init__Cs* D!&*,rc,<V^8dQhRS[RS[RS[/#)r r r!r)r)rr's"rrr(Os'ddVd6dfdrcZ\WVPVPVP4#r*)rrrr)r-r r!s&&&rforwardPSRoIAlign.forwardOs%E)9)94;M;MtObObccrc <V^8dQhRS[/#)r r)str)rr's"rrr(Rs#rcVPP RVP RVP RVP R2pV#)z (output_size=z, spatial_scale=z, sampling_ratio=))r.__name__rrr)r-ss& r__repr__PSRoIAlign.__repr__RsS~~&&'(++,t112 3 34   r)rrr) r8 __module__ __qualname____firstlineno____doc__r,r2r:__static_attributes____classdictcell__ __classcell__)r.r's@@rr%r%>s/ - -ddrr%)g?)rtorch.fxrrtorch.nn.modules.utilsrtorchvision.extensionrutilsr_utilsrr fxwraprModuler%rrrMsG (1'F//dr