+
     °³j6  ã                   óÆ   € ^ RI t ^ RIt ^ RI HtHt ^ RIHt ^ RIHt ^RIH	t	 ^RI
HtHt ] P                  P                  RR R ll4       t ! R	 R
]P                   4      tR# )é    N)ÚnnÚTensor)Ú_pair)Ú_assert_has_ops)Ú_log_api_usage_once)Úcheck_roi_boxes_shapeÚconvert_boxes_to_roi_formatc          
      óT   € V ^8„  d   QhR\         R\         R\        R\        R\         /# )é   ÚinputÚboxesÚoutput_sizeÚspatial_scaleÚreturn)r   ÚintÚfloat)Úformats   "Ú\/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/ops/ps_roi_pool.pyÚ__annotate__r      s:   € ÷ 'ñ 'Üð'äð'ô ð'ô ð	'ô
 ñ'ó    c                óÄ  € \         P                  P                  4       '       g4   \         P                  P                  4       '       g   \	        \
        4       \        4        \        V4       Tp\        V4      p\        V\         P                  4      '       g   \        V4      p\         P                  P                  P                  WW2^ ,          V^,          4      w  rVV# )aK  
Performs Position-Sensitive Region of Interest (RoI) Pool operator
described in R-FCN

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

Returns:
    Tensor[K, C / (output_size[0] * output_size[1]), output_size[0], output_size[1]]: The pooled RoIs.
)ÚtorchÚjitÚis_scriptingÚ
is_tracingr   Úps_roi_poolr   r   r   Ú
isinstancer   r	   ÚopsÚtorchvision)r   r   r   r   ÚroisÚoutputÚ_s   &&&&   r   r   r      sš   € ô> �9‰9×!Ñ!×#Ò#¬E¯I©I×,@Ñ,@×,BÒ,BÜœKÔ(ÜÔÜ˜%Ô Ø€DÜ˜Ó$€KÜ�dœEŸL™L×)Ò)Ü*¨4Ó0ˆÜ—	‘	×%Ñ%×1Ñ1°%¸}ÐZ[ÍnÐ^iÐjkÕ^lÓm�I€FØ€Mr   c                   óf   a a€ ] tR t^6t oRtV3R lV 3R lltV3R lR ltV3R lR ltRtVt	V ;t
# )	Ú	PSRoIPoolz
See :func:`ps_roi_pool`.
c                ó&   <€ V ^8„  d   QhRS[ RS[/# )r   r   r   )r   r   )r   Ú__classdict__s   "€r   r   ÚPSRoIPool.__annotate__;   s   ø€ ÷ +ñ +¡Cð +¹ñ +r   c                óR   <€ \         SV `  4        \        V 4       Wn        W n        R # ©N)ÚsuperÚ__init__r   r   r   )Úselfr   r   Ú	__class__s   &&&€r   r+   ÚPSRoIPool.__init__;   s"   ø€ Ü‰ÑÔÜ˜DÔ!Ø&ÔØ*Ör   c                ó,   <€ V ^8„  d   QhRS[ RS[ RS[ /# )r   r   r    r   )r   )r   r&   s   "€r   r   r'   A   s'   ø€ ÷ Nñ N™Vð N©6ð N±fñ Nr   c                óD   € \        WV P                  V P                  4      # r)   )r   r   r   )r,   r   r    s   &&&r   ÚforwardÚPSRoIPool.forwardA   s   € Ü˜5¨×(8Ñ(8¸$×:LÑ:LÓMÐMr   c                ó    <€ V ^8„  d   QhRS[ /# )r   r   )Ústr)r   r&   s   "€r   r   r'   D   s   ø€ ÷ ñ ™#ñ r   c                ól   € V P                   P                   R V P                   RV P                   R2pV# )z(output_size=z, spatial_scale=Ú))r-   Ú__name__r   r   )r,   Úss   & r   Ú__repr__ÚPSRoIPool.__repr__D   s;   € Ø�~‰~×&Ñ&Ð' }°T×5EÑ5EÐ4FÐFVÐW[×WiÑWiÐVjÐjkÐlˆØˆr   )r   r   )r7   Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__r+   r1   r9   Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r-   r&   s   @@r   r$   r$   6   s/   ù‡ € ñ÷+ó +÷Nð N÷÷ ð r   r$   )g      ð?)r   Útorch.fxr   r   Útorch.nn.modules.utilsr   Útorchvision.extensionr   Úutilsr   Ú_utilsr   r	   ÚfxÚwrapr   ÚModuler$   © r   r   Ú<module>rK      sG   ðÛ Û ß Ý (Ý 1å 'ß Fð ‡�‡�ö'ó ð'ôT�—	‘	ö r   