o oi@sddlmZddlmZddlZddlmZddlmZddlm Z m Z ddl m Z ddl mZ  ddddZGdddejZdS)) annotations)OptionalN)nn)Tensor) KORNIA_CHECKKORNIA_CHECK_IS_TENSOR)mask_ignore_pixels)one_hotmicro:0yE>predrtargetaveragestrepsfloatweightOptional[Tensor] ignore_index Optional[int]returncCst|t|jdkstd|j|jdd|jddks-td|jd|j|j|jks?td|jd|j|jd}d d h}t||vd |d ||jdd }t||\}} t||jd|j|j d} | dur| d| | } || }|durt|dt|jd|ko| |kd|d|jt|j|jkd|jd|jn| |jd}d} |d krdg| R} | ddd}||}| |} t|| | } t|| | } d| | |}| d}|d kr||d|}t|}|S)u0Criterion that computes Sørensen-Dice Coefficient loss. According to [1], we compute the Sørensen-Dice Coefficient as follows: .. math:: \text{Dice}(x, class) = \frac{2 |X \cap Y|}{|X| + |Y|} Where: - :math:`X` expects to be the scores of each class. - :math:`Y` expects to be the one-hot tensor with the class labels. the loss, is finally computed as: .. math:: \text{loss}(x, class) = 1 - \text{Dice}(x, class) Reference: [1] https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient Args: pred: logits tensor with shape :math:`(N, C, H, W)` where C = number of classes. target: labels tensor with shape :math:`(N, H, W)` where each value is :math:`0 ≤ targets[i] ≤ C-1`. average: Reduction applied in multi-class scenario: - ``'micro'`` [default]: Calculate the loss across all classes. - ``'macro'``: Calculate the loss for each class separately and average the metrics across classes. eps: Scalar to enforce numerical stabiliy. weight: weights for classes with shape :math:`(num\_of\_classes,)`. ignore_index: labels with this value are ignored in the loss computation. Return: One-element tensor of the computed loss. Example: >>> N = 5 # num_classes >>> pred = torch.randn(1, N, 3, 5, requires_grad=True) >>> target = torch.empty(1, 3, 5, dtype=torch.long).random_(N) >>> output = dice_loss(pred, target) >>> output.backward() z,Invalid pred shape, we expect BxNxHxW. Got: Nz.pred and target shapes must be the same. Got: z and z1pred and target must be in the same device. Got: r macrozThe `average` has to be one of z. Got: )dim) num_classesdevicedtypezweight must be Tensor or None.rz)weight shape must be (num_of_classes,): (z,), got z1weight and pred must be in the same device. Got: )g@g?)rlenshape ValueErrorrrsoftmaxrr r unsqueeze_numelnew_onesviewtorchsummean)r rrrrrnum_of_classespossible_average pred_soft target_masktarget_one_hotdims intersection cardinality dice_score dice_lossr8F/home/ubuntu/.local/lib/python3.10/site-packages/kornia/losses/dice.pyr7#sT4          r7cs6eZdZdZ    ddfdd ZdddZZS)DiceLossuCriterion that computes Sørensen-Dice Coefficient loss. According to [1], we compute the Sørensen-Dice Coefficient as follows: .. math:: \text{Dice}(x, class) = \frac{2 |X| \cap |Y|}{|X| + |Y|} Where: - :math:`X` expects to be the scores of each class. - :math:`Y` expects to be the one-hot tensor with the class labels. the loss, is finally computed as: .. math:: \text{loss}(x, class) = 1 - \text{Dice}(x, class) Reference: [1] https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient Args: average: Reduction applied in multi-class scenario: - ``'micro'`` [default]: Calculate the loss across all classes. - ``'macro'``: Calculate the loss for each class separately and average the metrics across classes. eps: Scalar to enforce numerical stabiliy. weight: weights for classes with shape :math:`(num\_of\_classes,)`. ignore_index: labels with this value are ignored in the loss computation. Shape: - Pred: :math:`(N, C, H, W)` where C = number of classes. - Target: :math:`(N, H, W)` where each value is :math:`0 ≤ targets[i] ≤ C-1`. Example: >>> N = 5 # num_classes >>> criterion = DiceLoss() >>> pred = torch.randn(1, N, 3, 5, requires_grad=True) >>> target = torch.empty(1, 3, 5, dtype=torch.long).random_(N) >>> output = criterion(pred, target) >>> output.backward() r r Nr rrrrrrrrrNonecs&t||_||_||_||_dSN)super__init__rrrr)selfrrrr __class__r8r9r>s  zDiceLoss.__init__r rrcCst|||j|j|j|jSr<)r7rrrr)r?r rr8r8r9forwardszDiceLoss.forwardr r Nr ) rrrrrrrrrr;)r rrrrr)__name__ __module__ __qualname____doc__r>rB __classcell__r8r8r@r9r:s/ r:rC)r rrrrrrrrrrrrr) __future__rtypingrr+r kornia.corerkornia.core.checkrrkornia.losses._utilsrkornia.utils.one_hotr r7Moduler:r8r8r8r9s        w