U
    (d
                     @   s|   d dl Z d dl mZmZ d dlmZ d dlmZ ddlmZ ddl	m
Z
mZ deeeeeedddZG dd dejZdS )    N)nnTensor)_pair)_assert_has_ops   )_log_api_usage_once   )convert_boxes_to_roi_formatcheck_roi_boxes_shape      ?)inputboxesoutput_sizespatial_scalesampling_ratioreturnc                 C   sr   t j st j stt t  t| |}t|}t	|t j
sJt|}t jj| |||d |d |\}}|S )aT  
    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
    r   r   )torchZjitZis_scripting
is_tracingr   ps_roi_alignr   r
   r   
isinstancer   r	   opsZtorchvision)r   r   r   r   r   roisoutput_ r   @/tmp/pip-unpacked-wheel-vx7f76es/torchvision/ops/ps_roi_align.pyr   
   s"    $     r   c                       sJ   e Zd ZdZeeed fddZeeedddZe	dd	d
Z
  ZS )
PSRoIAlignz#
    See :func:`ps_roi_align`.
    )r   r   r   c                    s(   t    t|  || _|| _|| _d S N)super__init__r   r   r   r   )selfr   r   r   	__class__r   r   r    A   s
    
zPSRoIAlign.__init__)r   r   r   c                 C   s   t ||| j| j| jS r   )r   r   r   r   )r!   r   r   r   r   r   forwardM   s    zPSRoIAlign.forward)r   c                 C   s*   | j j d| j d| j d| j d}|S )Nz(output_size=z, spatial_scale=z, sampling_ratio=))r#   __name__r   r   r   )r!   sr   r   r   __repr__P   s    $zPSRoIAlign.__repr__)r&   
__module____qualname____doc__intfloatr    r   r$   strr(   __classcell__r   r   r"   r   r   <   s   r   )r   r   )r   r   r   Ztorch.nn.modules.utilsr   Ztorchvision.extensionr   utilsr   _utilsr	   r
   r,   r-   r   Moduler   r   r   r   r   <module>   s      2