U (d@sJddlZddlmmZddlmZd ejejeee ejdddZ dS) N)_log_api_usage_once?none)inputstargetsalphagamma reductionreturnc Cstjstjsttt|}tj||dd}||d|d|}|d||}|dkr||d|d|} | |}|dkr| }n|dkr| }|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 rmeansum) torchZjitZ is_scripting is_tracingrsigmoid_focal_lossZsigmoidFZ binary_cross_entropy_with_logitsr r) rrrr r pZce_lossZp_tZlossZalpha_tr>/tmp/pip-unpacked-wheel-vx7f76es/torchvision/ops/focal_loss.pyrs  r)rrr) rZtorch.nn.functionalnnZ functionalrutilsrZTensorfloatstrrrrrrs