U tPh-@sddlmZddlZddlmZddlmZddlZddlm m Z ddl m Z ddlmZddlmZGdd d e Zdd d d d d dddZdd d d d d dddZdS)) annotationsN)Sequence)Optional)_Loss)one_hot) LossReductionc sXeZdZdZdddddejdfddddd d dd d fd d ZddddddZZS) FocalLossa FocalLoss is an extension of BCEWithLogitsLoss that down-weights loss from high confidence correct predictions. Reimplementation of the Focal Loss described in: - ["Focal Loss for Dense Object Detection"](https://arxiv.org/abs/1708.02002), T. Lin et al., ICCV 2017 - "AnatomyNet: Deep learning for fast and fully automated whole-volume segmentation of head and neck anatomy", Zhu et al., Medical Physics 2018 Example: >>> import torch >>> from monai.losses import FocalLoss >>> from torch.nn import BCEWithLogitsLoss >>> shape = B, N, *DIMS = 2, 3, 5, 7, 11 >>> input = torch.rand(*shape) >>> target = torch.rand(*shape) >>> # Demonstrate equivalence to BCE when gamma=0 >>> fl_g0_criterion = FocalLoss(reduction='none', gamma=0) >>> fl_g0_loss = fl_g0_criterion(input, target) >>> bce_criterion = BCEWithLogitsLoss(reduction='none') >>> bce_loss = bce_criterion(input, target) >>> assert torch.allclose(fl_g0_loss, bce_loss) >>> # Demonstrate "focus" by setting gamma > 0. >>> fl_g2_criterion = FocalLoss(reduction='none', gamma=2) >>> fl_g2_loss = fl_g2_criterion(input, target) >>> # Mark easy and hard cases >>> is_easy = (target > 0.7) & (input > 0.7) >>> is_hard = (target > 0.7) & (input < 0.3) >>> easy_loss_g0 = fl_g0_loss[is_easy].mean() >>> hard_loss_g0 = fl_g0_loss[is_hard].mean() >>> easy_loss_g2 = fl_g2_loss[is_easy].mean() >>> hard_loss_g2 = fl_g2_loss[is_hard].mean() >>> # Gamma > 0 causes the loss function to "focus" on the hard >>> # cases. IE, easy cases are downweighted, so hard cases >>> # receive a higher proportion of the loss. >>> hard_to_easy_ratio_g2 = hard_loss_g2 / easy_loss_g2 >>> hard_to_easy_ratio_g0 = hard_loss_g0 / easy_loss_g0 >>> assert hard_to_easy_ratio_g2 > hard_to_easy_ratio_g0 TF@Nboolfloatz float | Nonez3Sequence[float] | float | int | torch.Tensor | NonezLossReduction | strNone)include_background to_onehot_ygammaalphaweight reduction use_softmaxreturncsbtjt|jd||_||_||_||_||_||_ |dk rJt |nd}| d||dS)a Args: include_background: if False, channel index 0 (background category) is excluded from the loss calculation. If False, `alpha` is invalid when using softmax. to_onehot_y: whether to convert the label `y` into the one-hot format. Defaults to False. gamma: value of the exponent gamma in the definition of the Focal loss. Defaults to 2. alpha: value of the alpha in the definition of the alpha-balanced Focal loss. The value should be in [0, 1]. Defaults to None. weight: weights to apply to the voxels of each class. If None no weights are applied. The input can be a single value (same weight for all classes), a sequence of values (the length of the sequence should be the same as the number of classes. If not ``include_background``, the number of classes should not include the background category class 0). The value/values should be no less than 0. Defaults to None. reduction: {``"none"``, ``"mean"``, ``"sum"``} Specifies the reduction to apply to the output. Defaults to ``"mean"``. - ``"none"``: no reduction will be applied. - ``"mean"``: the sum of the output will be divided by the number of elements in the output. - ``"sum"``: the output will be summed. use_softmax: whether to use softmax to transform the original logits into probabilities. If True, softmax is used. If False, sigmoid is used. Defaults to False. Example: >>> import torch >>> from monai.losses import FocalLoss >>> pred = torch.tensor([[1, 0], [0, 1], [1, 0]], dtype=torch.float32) >>> grnd = torch.tensor([[0], [1], [0]], dtype=torch.int64) >>> fl = FocalLoss(to_onehot_y=True) >>> fl(pred, grnd) )rN class_weight) super__init__rvaluer rrrrrtorch as_tensorregister_buffer)selfr rrrrrr __class__L/home/dell461/cl/sdc2/HISourceFinder-master-l/src/monai/losses/focal_loss.pyrDs) zFocalLoss.__init__ torch.Tensor)inputtargetrcCs4|jd}|jr0|dkr$tdn t||d}|jsr|dkrJtdn(|ddddf}|ddddf}|j|jkrtd|jd|jdd}|}|}|jr|js|j dk rd|_ td t |||j |j }nt |||j |j }|jd}|j dk r|dkr|j jd kr|jtjjkr |}n$|jtjjkrntd|jd|S)a Args: input: the shape should be BNH[WD], where N is the number of classes. The input should be the original logits since it will be transformed by a sigmoid/softmax in the forward function. target: the shape should be BNH[WD] or B1H[WD], where N is the number of classes. Raises: ValueError: When input and target (after one hot transform if set) have different shapes. ValueError: When ``self.reduction`` is not one of ["mean", "sum", "none"]. ValueError: When ``self.weight`` is a sequence and the length is not equal to the number of classes. ValueError: When ``self.weight`` is/contains a value that is less than 0. z6single channel prediction, `to_onehot_y=True` ignored.) num_classesz>single channel prediction, `include_background=False` ignored.Nz"ground truth has different shape (z) from input ()z?`include_background=False`, `alpha` ignored when using softmax.rzthe length of the `weight` sequence should be the same as the number of classes. If `include_background=False`, the weight should not include the background category class 0.z:the value/values of the `weight` should be no less than 0.T)dimzUnsupported reduction: z0, available options are ["mean", "sum", "none"].)shaperwarningswarnrr ValueErrorr rrsoftmax_focal_lossrsigmoid_focal_lossrndimrrmintolenviewrrSUMrmeanlistrangesumMEANNONE)rr"r# n_pred_chlossnum_of_classesbroadcast_dimsZaverage_spatial_dimsrrr forwardxs\          zFocalLoss.forward) __name__ __module__ __qualname____doc__rr:rr@ __classcell__rrrr rs+"4rr r!r zOptional[float])r"r#rrrcCs|d}d|| ||}|dk rtd|g|g|jdd|}dgdgt|jdd}||}||}|S)z FL(pt) = -alpha * (1 - pt)**gamma * log(pt) where p_i = exp(s_i) / sum_j exp(s_j), t is the target (ground truth) class, and s_j is the unnormalized score for class j. r$Nr'r() log_softmaxexppowrtensorr*r2r3r4)r"r#rrZinput_lsr=Z alpha_facr?rrr r.s * r.cCsj|||t|}t| |dd}|||}|dk rf||d|d|}||}|S)z| FL(pt) = -alpha * (1 - pt)**gamma * log(pt) where p = sigmoid(x), pt = p if label is 1 or 1 - p if label is 0 r(r$N)F logsigmoidrG)r"r#rrr=ZinvprobsZ alpha_factorrrr r/s r/)r N)r N) __future__rr+collections.abcrtypingrrtorch.nn.functionalnn functionalrJtorch.nn.modules.lossrmonai.networksr monai.utilsrrr.r/rrrr  s      5