3jSSKJr SSKJr SSKrSSKJrJr SSKJrJ r J r S S Sjjr "SS\R5r g) ) annotations)OptionalN)Tensornn) KORNIA_CHECKKORNIA_CHECK_IS_TENSORKORNIA_CHECK_SHAPEc[U/SQ5 [U/SQ5 URSS:d[SUR35eURSSURSS:Xd%[SURSUR35eURUR:Xd%[S URSUR35eURSnUb[ US 5 [ URS U:H=(a UR 5U:HS US UR35 [ URUR:HSURSUR35 URURS URSS5nURURS S5nURupgnURS5n [RRRUR[R5US9RS SS5RUR 5n X- R#5n [R$"U SSS9up[R&"X`RS9R)S5R)S5R+XgU5nX^U 4nUR-SSS9nUUR/S5- nUSU- R/S5-nSUU- - nUS:aUSSS24USSS24- USSS24'U U-nUR-S5R1S 5nUbUU-nUR15nU$)uCriterion that computes a surrogate multi-class intersection-over-union (IoU) loss. According to [1], we compute the IoU as follows: .. math:: \text{IoU}(x, class) = \frac{|X \cap Y|}{|X \cup Y|} [1] approximates this fomular with a surrogate, which is fully differentable. Where: - :math:`X` expects to be the scores of each class. - :math:`Y` expects to be the long tensor with the class labels. the loss, is finally computed as: .. math:: \text{loss}(x, class) = 1 - \text{IoU}(x, class) Reference: [1] https://arxiv.org/pdf/1705.08790.pdf .. note:: This loss function only supports multi-class (C > 1) labels. For binary labels please use the Lovasz-Hinge loss. Args: pred: logits tensor with shape :math:`(N, C, H, W)` where C = number of classes > 1. target: labels tensor with shape :math:`(N, H, W)` where each value is in range :math:`0 ≤ targets[i] ≤ C-1`. weight: weights for classes with shape :math:`(num\_of\_classes,)`. Return: a scalar with 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 = lovasz_softmax_loss(pred, target) >>> output.backward() )BNHW)r r rz8Invalid pred shape, we expect BxNxHxW, with N > 1. Got: Nz.pred and target shapes must be the same. Got: z and z1pred and target must be in the same device. Got: zweight 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: ) num_classesT)dim descending)device)keepdimg?.)r shape ValueErrorrrrnumelreshapesoftmaxtorchr functionalone_hottoint64permutedtypeabssortarange unsqueezeexpandsumcumsummean)predtargetweightnum_of_classes pred_flattentarget_flattenr Cr pred_soft foregrounderrors errors_sorted permutations batch_index target_sortedtarget_sorted_sum intersectionuniongradientweighted_errorsloss_per_class final_losss V/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/losses/lovasz_softmax.pylovasz_softmax_lossrBsFZt12v/ ::a=1 STXT^T^S_`aa ::bc?fll23/ /I$**UZ[a[g[gZhijj ;;&-- 'LT[[MY^_e_l_l^mnooZZ]N v'GH \\!_ . S6<<>^3S77GxPVP\P\~ ^   MMT[[ (? eTXT_T_S` a  << 1 tzz!}bIL#^^FLLOR@N  GA!%,,Q/I ##N$5$5ekk$BPQ#RZZ[\^_abcffgkgqgqr ,113F"'**Vt"LM,,q5??BLLQOVVWX]^_K" #<=M%))!T):$}';';A'>>L }!4 < ^\rSrSrSrSSU4SjjjrSSjrSrU=r$) LovaszSoftmaxLossu#Criterion that computes a surrogate multi-class intersection-over-union (IoU) loss. According to [1], we compute the IoU as follows: .. math:: \text{IoU}(x, class) = \frac{|X \cap Y|}{|X \cup Y|} [1] approximates this fomular with a surrogate, which is fully differentable. Where: - :math:`X` expects to be the scores of each class. - :math:`Y` expects to be the binary tensor with the class labels. the loss, is finally computed as: .. math:: \text{loss}(x, class) = 1 - \text{IoU}(x, class) Reference: [1] https://arxiv.org/pdf/1705.08790.pdf .. note:: This loss function only supports multi-class (C > 1) labels. For binary labels please use the Lovasz-Hinge loss. Args: pred: logits tensor with shape :math:`(N, C, H, W)` where C = number of classes > 1. labels: labels tensor with shape :math:`(N, H, W)` where each value is in range :math:`0 ≤ targets[i] ≤ C-1`. weight: weights for classes with shape :math:`(num\_of\_classes,)`. Return: a scalar with the computed loss. Example: >>> N = 5 # num_classes >>> criterion = LovaszSoftmaxLoss() >>> 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() c.>[TU]5 XlgN)super__init__r.)selfr. __class__s rArJLovaszSoftmaxLoss.__init__s  rCc*[XURS9$)N)r,r-r.)rBr.)rKr,r-s rAforwardLovaszSoftmaxLoss.forwards"DKKPPrC)r.rH)r.Optional[Tensor]returnNone)r,rr-rrRr) __name__ __module__ __qualname____firstlineno____doc__rJrO__static_attributes__ __classcell__)rLs@rArErEs,\QQrCrErH)r,rr-rr.rQrRr) __future__rtypingrrrrkornia.core.checkrrr rBModulerErCrAr`s2$# VV dN4Q 4QrC