o .wiP@sddlmZddlmZddlmZddlmZmZm Z m Z m Z m Z m Z mZmZmZmZmZddlmZmZddlmZ  d.d ed ed ed ed eeddeddedefddZ    d/dededededdeededefddZ    d0deded!ed eed"d#ededdeededefd$d%Z     d1deded&eded eed"deddeededefd'd(Z    )   d2deded*ed+ded!eed&eed eed"deedd#eedeededefd,d-ZdS)3)Optional)Tensor)Literal) "_binary_stat_scores_arg_validation_binary_stat_scores_format%_binary_stat_scores_tensor_validation_binary_stat_scores_update&_multiclass_stat_scores_arg_validation_multiclass_stat_scores_format)_multiclass_stat_scores_tensor_validation_multiclass_stat_scores_update&_multilabel_stat_scores_arg_validation_multilabel_stat_scores_format)_multilabel_stat_scores_tensor_validation_multilabel_stat_scores_update)_adjust_weights_safe_divide _safe_divide)ClassificationTaskglobalFtpfptnfnaverage)binarymicromacroweightednonemultidim_average)r samplewise multilabelreturncCs|dkrdt||||||S|dkra|j|dkrdndd}|j|dkr+dndd}|rX|j|dkr9dndd}|j|dkrEdndd}dt||||||Sdt|||S|rrdt||||||ndt|||}t||||||S)a]Reduce classification statistics into hamming distance. Args: tp: number of true positives fp: number of false positives tn: number of true negatives fn: number of false negatives average: Defines the reduction that is applied over labels. Should be one of the following: - ``binary``: for binary reduction - ``micro``: sum score over all classes/labels - ``macro``: salculate score for each class/label and average them - ``weighted``: calculates score for each class/label and computes weighted average using their support - ``"none"`` or ``None``: calculates score for each class/label and applies no reduction multidim_average: Defines how additionally dimensions ``...`` should be handled. Should be one of the following: - ``global``: Additional dimensions are flatted along the batch dimension - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis. multilabel: If input is multilabel or not rrrr)dim)rsumr)rrrrrrr!scorer'k/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/functional/classification/hamming.py_hamming_distance_reduce%s"4r)?NTpredstarget threshold ignore_index validate_argsc CsX|rt|||t||||t||||\}}t|||\}}}} t|||| d|dS)a Compute the average `Hamming distance`_ (also known as Hamming loss) for binary tasks. .. math:: \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il}) Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions, and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that tensor. Accepts the following input tensors: - ``preds`` (int or float tensor): ``(N, ...)``. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Additionally, we convert to int tensor with thresholding using the value in ``threshold``. - ``target`` (int tensor): ``(N, ...)`` Args: preds: Tensor with predictions target: Tensor with true labels threshold: Threshold for transforming probability to binary {0,1} predictions multidim_average: Defines how additionally dimensions ``...`` should be handled. Should be one of the following: - ``global``: Additional dimensions are flatted along the batch dimension - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis. The statistics in this case are calculated over the additional dimensions. 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. Returns: If ``multidim_average`` is set to ``global``, the metric returns a scalar value. If ``multidim_average`` is set to ``samplewise``, the metric returns ``(N,)`` vector consisting of a scalar value per sample. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.functional.classification import binary_hamming_distance >>> target = tensor([0, 1, 0, 1, 0, 1]) >>> preds = tensor([0, 0, 1, 1, 0, 1]) >>> binary_hamming_distance(preds, target) tensor(0.3333) Example (preds is float tensor): >>> from torchmetrics.functional.classification import binary_hamming_distance >>> target = tensor([0, 1, 0, 1, 0, 1]) >>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92]) >>> binary_hamming_distance(preds, target) tensor(0.3333) Example (multidim tensors): >>> from torchmetrics.functional.classification import binary_hamming_distance >>> target = tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]]) >>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]], ... [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]]) >>> binary_hamming_distance(preds, target, multidim_average='samplewise') tensor([0.6667, 0.8333]) rrr)rrrrr)) r+r,r-rr.r/rrrrr'r'r(binary_hamming_distanceVs D r1rr# num_classes)rrrrtop_kc Csd|rt|||||t|||||t|||\}}t|||||||\}} } } t|| | | ||dS)a^Compute the average `Hamming distance`_ (also known as Hamming loss) for multiclass tasks. .. math:: \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il}) Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions, and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that tensor. Accepts the following input tensors: - ``preds``: ``(N, ...)`` (int tensor) or ``(N, C, ..)`` (float tensor). If preds is a floating point we apply ``torch.argmax`` along the ``C`` dimension to automatically convert probabilities/logits into an int tensor. - ``target`` (int tensor): ``(N, ...)`` Args: preds: Tensor with predictions target: Tensor with true labels num_classes: Integer specifying the number of classes average: Defines the reduction that is applied over labels. Should be one of the following: - ``micro``: Sum statistics over all labels - ``macro``: Calculate statistics for each label and average them - ``weighted``: calculates statistics for each label and computes weighted average using their support - ``"none"`` or ``None``: calculates statistic for each label and applies no reduction top_k: Number of highest probability or logit score predictions considered to find the correct label. Only works when ``preds`` contain probabilities/logits. multidim_average: Defines how additionally dimensions ``...`` should be handled. Should be one of the following: - ``global``: Additional dimensions are flatted along the batch dimension - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis. The statistics in this case are calculated over the additional dimensions. 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. Returns: The returned shape depends on the ``average`` and ``multidim_average`` arguments: - If ``multidim_average`` is set to ``global``: - If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor - If ``average=None/'none'``, the shape will be ``(C,)`` - If ``multidim_average`` is set to ``samplewise``: - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)`` - If ``average=None/'none'``, the shape will be ``(N, C)`` Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.functional.classification import multiclass_hamming_distance >>> target = tensor([2, 1, 0, 0]) >>> preds = tensor([2, 1, 0, 1]) >>> multiclass_hamming_distance(preds, target, num_classes=3) tensor(0.1667) >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None) tensor([0.5000, 0.0000, 0.0000]) Example (preds is float tensor): >>> from torchmetrics.functional.classification import multiclass_hamming_distance >>> target = tensor([2, 1, 0, 0]) >>> preds = tensor([[0.16, 0.26, 0.58], ... [0.22, 0.61, 0.17], ... [0.71, 0.09, 0.20], ... [0.05, 0.82, 0.13]]) >>> multiclass_hamming_distance(preds, target, num_classes=3) tensor(0.1667) >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None) tensor([0.5000, 0.0000, 0.0000]) Example (multidim tensors): >>> from torchmetrics.functional.classification import multiclass_hamming_distance >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]]) >>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]]) >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise') tensor([0.5000, 0.7222]) >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise', average=None) tensor([[0.0000, 1.0000, 0.5000], [1.0000, 0.6667, 0.5000]]) r0)r r r r r)) r+r,r2rr3rr.r/rrrrr'r'r(multiclass_hamming_distancesc r4 num_labelsc Csb|rt|||||t|||||t|||||\}}t|||\}} } } t|| | | ||ddS)aCompute the average `Hamming distance`_ (also known as Hamming loss) for multilabel tasks. .. math:: \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il}) Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions, and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that tensor. Accepts the following input tensors: - ``preds`` (int or float tensor): ``(N, C, ...)``. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Additionally, we convert to int tensor with thresholding using the value in ``threshold``. - ``target`` (int tensor): ``(N, C, ...)`` Args: preds: Tensor with predictions target: Tensor with true labels num_labels: Integer specifying the number of labels threshold: Threshold for transforming probability to binary (0,1) predictions average: Defines the reduction that is applied over labels. Should be one of the following: - ``micro``: Sum statistics over all labels - ``macro``: Calculate statistics for each label and average them - ``weighted``: calculates statistics for each label and computes weighted average using their support - ``"none"`` or ``None``: calculates statistic for each label and applies no reduction multidim_average: Defines how additionally dimensions ``...`` should be handled. Should be one of the following: - ``global``: Additional dimensions are flatted along the batch dimension - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis. The statistics in this case are calculated over the additional dimensions. 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. Returns: The returned shape depends on the ``average`` and ``multidim_average`` arguments: - If ``multidim_average`` is set to ``global``: - If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor - If ``average=None/'none'``, the shape will be ``(C,)`` - If ``multidim_average`` is set to ``samplewise``: - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)`` - If ``average=None/'none'``, the shape will be ``(N, C)`` Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.functional.classification import multilabel_hamming_distance >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0, 0, 1], [1, 0, 1]]) >>> multilabel_hamming_distance(preds, target, num_labels=3) tensor(0.3333) >>> multilabel_hamming_distance(preds, target, num_labels=3, average=None) tensor([0.0000, 0.5000, 0.5000]) Example (preds is float tensor): >>> from torchmetrics.functional.classification import multilabel_hamming_distance >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]]) >>> multilabel_hamming_distance(preds, target, num_labels=3) tensor(0.3333) >>> multilabel_hamming_distance(preds, target, num_labels=3, average=None) tensor([0.0000, 0.5000, 0.5000]) Example (multidim tensors): >>> from torchmetrics.functional.classification import multilabel_hamming_distance >>> target = tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]]) >>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]], ... [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]]) >>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise') tensor([0.6667, 0.8333]) >>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise', average=None) tensor([[0.5000, 0.5000, 1.0000], [1.0000, 1.0000, 0.5000]]) T)rrr!)r rrrr)) r+r,r5r-rrr.r/rrrrr'r'r(multilabel_hamming_distances _r6rtask)r multiclassr!c Cst|}|dus J|tjkrt||||| | S|tjkrGt|ts-tdt|dt|ts>> from torch import tensor >>> target = tensor([[0, 1], [1, 1]]) >>> preds = tensor([[0, 1], [0, 1]]) >>> hamming_distance(preds, target, task="binary") tensor(0.2500) Nz+`num_classes` is expected to be `int` but `z was passed.`z%`top_k` is expected to be `int` but `z*`num_labels` is expected to be `int` but `zNot handled value: ) rfrom_strBINARYr1 MULTICLASS isinstanceint ValueErrortyper4 MULTILABELr6) r+r,r7r-r2r5rrr3r.r/r'r'r(hamming_distancevs& %       rA)rF)r*rNT)rr#rNT)r*rrNT)r*NNrrr#NT) typingrtorchrtyping_extensionsr2torchmetrics.functional.classification.stat_scoresrrrrr r r r r rrrtorchmetrics.utilities.computerrtorchmetrics.utilities.enumsrboolr)floatr=r1r4r6rAr'r'r'r(s  8    4 P  q  k