o yi1@sddlmZmZddlZddlmZddlmZddlmZm Z m Z m Z m Z m Z mZmZmZddlmZddlmZGdd d eZGd d d eZGd d d ZdS))AnyOptionalN)Tensor)Literal) (_binary_calibration_error_arg_validation+_binary_calibration_error_tensor_validation _binary_calibration_error_update_binary_confusion_matrix_format _ce_compute,_multiclass_calibration_error_arg_validation/_multiclass_calibration_error_tensor_validation$_multiclass_calibration_error_update#_multiclass_confusion_matrix_format)Metric) dim_zero_catc seZdZUdZdZeed<dZeed<dZeed<    dd e d e d d e e dede ddf fdd Z dededdfddZdefddZZS)BinaryCalibrationErrora `Top-label Calibration Error`_ for binary tasks. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution. Three different norms are implemented, each corresponding to variations on the calibration error metric. .. math:: \text{ECE} = \sum_i^N b_i \|(p_i - c_i)\|, \text{L1 norm (Expected Calibration Error)} .. math:: \text{MCE} = \max_{i} (p_i - c_i), \text{Infinity norm (Maximum Calibration Error)} .. math:: \text{RMSCE} = \sqrt{\sum_i^N b_i(p_i - c_i)^2}, \text{L2 norm (Root Mean Square Calibration Error)} Where :math:`p_i` is the top-1 prediction accuracy in bin :math:`i`, :math:`c_i` is the average confidence of predictions in bin :math:`i`, and :math:`b_i` is the fraction of data points in bin :math:`i`. Bins are constructed in an uniform way in the [0,1] range. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, ...)`` containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` containing ground truth labels, and therefore only contain {0,1} values (except if `ignore_index` is specified). The value 1 always encodes the positive class. As output to ``forward`` and ``compute`` the metric returns the following output: - ``bce`` (:class:`~torch.Tensor`): A scalar tensor containing the calibration error Additional dimension ``...`` will be flattened into the batch dimension. Args: n_bins: Number of bins to use when computing the metric. norm: Norm used to compare empirical and expected probability bins. ignore_index: Specifies a target value that is ignored and does not contribute to the metric calculation validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torchmetrics.classification import BinaryCalibrationError >>> preds = torch.tensor([0.25, 0.25, 0.55, 0.75, 0.75]) >>> target = torch.tensor([0, 0, 1, 1, 1]) >>> metric = BinaryCalibrationError(n_bins=2, norm='l1') >>> metric(preds, target) tensor(0.2900) >>> bce = BinaryCalibrationError(n_bins=2, norm='l2') >>> bce(preds, target) tensor(0.2918) >>> bce = BinaryCalibrationError(n_bins=2, norm='max') >>> bce(preds, target) tensor(0.3167) Fis_differentiablehigher_is_betterfull_state_updatel1NTn_binsnormrl2max ignore_index validate_argskwargsreturnc s^tjdi||rt|||||_||_||_||_|jdgdd|jdgdddSN confidencescat)dist_reduce_fx accuracies)super__init__rrrrr add_state)selfrrrrr __class__r%a/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/classification/calibration_error.pyr'as zBinaryCalibrationError.__init__predstargetcCsV|jr t|||jt||d|jdd\}}t||\}}|j||j|dS)NgF) thresholdrconvert_to_labels)rrrr rr!appendr$r)r-r.r!r$r%r%r,updatess   zBinaryCalibrationError.updatecC(t|j}t|j}t|||j|jdSN)rrr!r$r rrr)r!r$r%r%r,compute}  zBinaryCalibrationError.computerrNT__name__ __module__ __qualname____doc__rbool__annotations__rrintrrrr'rr3r8 __classcell__r%r%r*r,r#s0  9   rcseZdZUdZdZeed<dZeed<dZeed<    dd e d e d e d de e dede ddffdd Z dededdfddZdefddZZS)MulticlassCalibrationErrora `Top-label Calibration Error`_ for multiclass tasks. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution. Three different norms are implemented, each corresponding to variations on the calibration error metric. .. math:: \text{ECE} = \sum_i^N b_i \|(p_i - c_i)\|, \text{L1 norm (Expected Calibration Error)} .. math:: \text{MCE} = \max_{i} (p_i - c_i), \text{Infinity norm (Maximum Calibration Error)} .. math:: \text{RMSCE} = \sqrt{\sum_i^N b_i(p_i - c_i)^2}, \text{L2 norm (Root Mean Square Calibration Error)} Where :math:`p_i` is the top-1 prediction accuracy in bin :math:`i`, :math:`c_i` is the average confidence of predictions in bin :math:`i`, and :math:`b_i` is the fraction of data points in bin :math:`i`. Bins are constructed in an uniform way in the [0,1] range. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, C, ...)`` containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider the input to be logits and will auto apply softmax per sample. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` containing ground truth labels, and therefore only contain values in the [0, n_classes-1] range (except if `ignore_index` is specified). .. note:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns the following output: - ``mcce`` (:class:`~torch.Tensor`): A scalar tensor containing the calibration error Args: num_classes: Integer specifing the number of classes n_bins: Number of bins to use when computing the metric. norm: Norm used to compare empirical and expected probability bins. ignore_index: Specifies a target value that is ignored and does not contribute to the metric calculation validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torchmetrics.classification import MulticlassCalibrationError >>> preds = torch.tensor([[0.25, 0.20, 0.55], ... [0.55, 0.05, 0.40], ... [0.10, 0.30, 0.60], ... [0.90, 0.05, 0.05]]) >>> target = torch.tensor([0, 1, 2, 0]) >>> metric = MulticlassCalibrationError(num_classes=3, n_bins=3, norm='l1') >>> metric(preds, target) tensor(0.2000) >>> mcce = MulticlassCalibrationError(num_classes=3, n_bins=3, norm='l2') >>> mcce(preds, target) tensor(0.2082) >>> mcce = MulticlassCalibrationError(num_classes=3, n_bins=3, norm='max') >>> mcce(preds, target) tensor(0.2333) FrrrrrNT num_classesrrrrrrrc sftjdi||rt||||||_||_||_||_||_|jdgdd|jdgdddSr ) r&r'r rrErrrr()r)rErrrrrr*r%r,r's z#MulticlassCalibrationError.__init__r-r.cCsX|jr t|||j|jt|||jdd\}}t||\}}|j||j|dS)NF)rr0) rr rErrr r!r1r$r2r%r%r,r3s   z!MulticlassCalibrationError.updatecCr4r5r6r7r%r%r,r8r9z"MulticlassCalibrationError.computer:r;r%r%r*r,rDs4  =   rDc@sXeZdZdZ      ddedded ed d eed eed edede fddZ dS)CalibrationErroraA`Top-label Calibration Error`_. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution. Three different norms are implemented, each corresponding to variations on the calibration error metric. .. math:: \text{ECE} = \sum_i^N b_i \|(p_i - c_i)\|, \text{L1 norm (Expected Calibration Error)} .. math:: \text{MCE} = \max_{i} (p_i - c_i), \text{Infinity norm (Maximum Calibration Error)} .. math:: \text{RMSCE} = \sqrt{\sum_i^N b_i(p_i - c_i)^2}, \text{L2 norm (Root Mean Square Calibration Error)} Where :math:`p_i` is the top-1 prediction accuracy in bin :math:`i`, :math:`c_i` is the average confidence of predictions in bin :math:`i`, and :math:`b_i` is the fraction of data points in bin :math:`i`. Bins are constructed in an uniform way in the [0,1] range. This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the ``task`` argument to either ``'binary'`` or ``'multiclass'``. See the documentation of :mod:`BinaryCalibrationError` and :mod:`MulticlassCalibrationError` for the specific details of each argument influence and examples. NrrTtask)binary multiclassrrrrErrrrcKs`|t||||d|dkrtdi|S|dkr)t|ts!Jt|fi|Std|)N)rrrrrHrIz[Expected argument `task` to either be `'binary'`, `'multiclass'` or `'multilabel'` but got r%)r3dictr isinstancerBrD ValueError)clsrGrrrErrrr%r%r,__new__s zCalibrationError.__new__)NrrNNT) r<r=r>r?rrBrr@rrrNr%r%r%r,rFs2 rF)typingrrtorchrtyping_extensionsr8torchmetrics.functional.classification.calibration_errorrrrr r r r r rtorchmetrics.metricrtorchmetrics.utilities.datarrrDrFr%r%r%r,s   , `f