U
    (d                     @   sJ   d dl Z d dlm  mZ ddlmZ d	e je jeee	e jdddZ
dS )
    N   )_log_api_usage_once      ?none)inputstargetsalphagamma	reductionreturnc           
      C   s   t j st j stt t | }tj| |dd}|| d| d|   }|d| |  }|dkr|| d| d|   }	|	| }|dkr|	 }n|dkr|
 }|S )a  
    Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002.

    Args:
        inputs (Tensor): A float tensor of arbitrary shape.
                The predictions for each example.
        targets (Tensor): A float tensor with the same shape as inputs. Stores the binary
                classification label for each element in inputs
                (0 for the negative class and 1 for the positive class).
        alpha (float): Weighting factor in range (0,1) to balance
                positive vs negative examples or -1 for ignore. Default: ``0.25``.
        gamma (float): Exponent of the modulating factor (1 - p_t) to
                balance easy vs hard examples. Default: ``2``.
        reduction (string): ``'none'`` | ``'mean'`` | ``'sum'``
                ``'none'``: No reduction will be applied to the output.
                ``'mean'``: The output will be averaged.
                ``'sum'``: The output will be summed. Default: ``'none'``.
    Returns:
        Loss tensor with the reduction option applied.
    r   )r
      r   meansum)torchZjitZis_scripting
is_tracingr   sigmoid_focal_lossZsigmoidFZ binary_cross_entropy_with_logitsr   r   )
r   r   r   r	   r
   pZce_lossZp_tZlossZalpha_t r   >/tmp/pip-unpacked-wheel-vx7f76es/torchvision/ops/focal_loss.pyr      s    

r   )r   r   r   )r   Ztorch.nn.functionalnnZ
functionalr   utilsr   ZTensorfloatstrr   r   r   r   r   <module>   s      