o .wi@s(ddlmZddlmZmZmZddlmZddlm Z ddl m Z ddl m Z mZmZddlmZddlmZdd lmZdd lmZdd lmZmZesRgd ZGd dde ZGdddeZGdddeZGddde ZGdddeZ GdddeZ!Gddde Z"Gddde Z#dS))Sequence)AnyOptionalUnion)Tensor)Literal)_ClassificationTaskWrapper)BinaryStatScoresMulticlassStatScoresMultilabelStatScores)_precision_recall_reduce)Metric)ClassificationTask)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE)BinaryPrecision.plotMulticlassPrecision.plotMultilabelPrecision.plotBinaryRecall.plotMulticlassRecall.plotMultilabelRecall.plotc@eZdZUdZdZeed<dZeeed<dZ eed<dZ e ed<d Z e ed <d e fd d Z ddeee ee fdeed efddZdS)BinaryPrecisiona Compute `Precision`_ for binary tasks. .. math:: \text{Precision} = \frac{\text{TP}}{\text{TP} + \text{FP}} Where :math:`\text{TP}` and :math:`\text{FP}` represent the number of true positives and false positives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FP} \neq 0`. If this case is encountered a score of `zero_division` (0 or 1, default is 0) is returned. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A int or float tensor of shape ``(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`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``. As output to ``forward`` and ``compute`` the metric returns the following output: - ``bp`` (:class:`~torch.Tensor`): 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. If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present, which the reduction will then be applied over instead of the sample dimension ``N``. Args: 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. zero_division: Should be `0` or `1`. The value returned when :math:`\text{TP} + \text{FP} = 0`. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.classification import BinaryPrecision >>> target = tensor([0, 1, 0, 1, 0, 1]) >>> preds = tensor([0, 0, 1, 1, 0, 1]) >>> metric = BinaryPrecision() >>> metric(preds, target) tensor(0.6667) Example (preds is float tensor): >>> from torchmetrics.classification import BinaryPrecision >>> target = tensor([0, 1, 0, 1, 0, 1]) >>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92]) >>> metric = BinaryPrecision() >>> metric(preds, target) tensor(0.6667) Example (multidim tensors): >>> from torchmetrics.classification import BinaryPrecision >>> 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]]]) >>> metric = BinaryPrecision(multidim_average='samplewise') >>> metric(preds, target) tensor([0.4000, 0.0000]) Fis_differentiableThigher_is_betterfull_state_updateplot_lower_bound?plot_upper_boundreturnc C,|\}}}}td||||d|j|jdS)Compute metric. precisionbinaryaveragemultidim_average zero_division _final_stater r(r)selftpfptnfnr2i/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/classification/precision_recall.pycomputeszBinaryPrecision.computeNvalaxcC |||S)a5Plot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure object and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting a single value >>> from torchmetrics.classification import BinaryPrecision >>> metric = BinaryPrecision() >>> metric.update(rand(10), randint(2,(10,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting multiple values >>> from torchmetrics.classification import BinaryPrecision >>> metric = BinaryPrecision() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(rand(10), randint(2,(10,)))) >>> fig_, ax_ = metric.plot(values) _plotr-r6r7r2r2r3plot (rNN__name__ __module__ __qualname____doc__rbool__annotations__rrrrfloatr rr4rrrrr<r2r2r2r3r)  C   rc@eZdZUdZdZeed<dZeeed<dZ eed<dZ e ed<d Z e ed <d Z eed <d efddZ ddeeeeefdeed efddZdS)MulticlassPrecisionaCompute `Precision`_ for multiclass tasks. .. math:: \text{Precision} = \frac{\text{TP}}{\text{TP} + \text{FP}} Where :math:`\text{TP}` and :math:`\text{FP}` represent the number of true positives and false positives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FP} \neq 0`. If this case is encountered for any class, the metric for that class will be set to `zero_division` (0 or 1, default is 0) and the overall metric may therefore be affected in turn. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` or float tensor of shape ``(N, C, ..)``. If preds is a floating point we apply ``torch.argmax`` along the ``C`` dimension to automatically convert probabilities/logits into an int tensor. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``. As output to ``forward`` and ``compute`` the metric returns the following output: - ``mcp`` (:class:`~torch.Tensor`): 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)`` If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present, which the reduction will then be applied over instead of the sample dimension ``N``. Args: 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. zero_division: Should be `0` or `1`. The value returned when :math:`\text{TP} + \text{FP} = 0`. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.classification import MulticlassPrecision >>> target = tensor([2, 1, 0, 0]) >>> preds = tensor([2, 1, 0, 1]) >>> metric = MulticlassPrecision(num_classes=3) >>> metric(preds, target) tensor(0.8333) >>> mcp = MulticlassPrecision(num_classes=3, average=None) >>> mcp(preds, target) tensor([1.0000, 0.5000, 1.0000]) Example (preds is float tensor): >>> from torchmetrics.classification import MulticlassPrecision >>> 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]]) >>> metric = MulticlassPrecision(num_classes=3) >>> metric(preds, target) tensor(0.8333) >>> mcp = MulticlassPrecision(num_classes=3, average=None) >>> mcp(preds, target) tensor([1.0000, 0.5000, 1.0000]) Example (multidim tensors): >>> from torchmetrics.classification import MulticlassPrecision >>> 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]]]) >>> metric = MulticlassPrecision(num_classes=3, multidim_average='samplewise') >>> metric(preds, target) tensor([0.3889, 0.2778]) >>> mcp = MulticlassPrecision(num_classes=3, multidim_average='samplewise', average=None) >>> mcp(preds, target) tensor([[0.6667, 0.0000, 0.5000], [0.0000, 0.5000, 0.3333]]) FrTrrrrrr Classplot_legend_namer!c C2|\}}}}td|||||j|j|j|jd S)r#r$r'r(top_kr)r+r r'r(rNr)r,r2r2r3r4zMulticlassPrecision.computeNr6r7cCr8)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure object and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> from torch import randint >>> # Example plotting a single value per class >>> from torchmetrics.classification import MulticlassPrecision >>> metric = MulticlassPrecision(num_classes=3, average=None) >>> metric.update(randint(3, (20,)), randint(3, (20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import randint >>> # Example plotting a multiple values per class >>> from torchmetrics.classification import MulticlassPrecision >>> metric = MulticlassPrecision(num_classes=3, average=None) >>> values = [] >>> for _ in range(20): ... values.append(metric(randint(3, (20,)), randint(3, (20,)))) >>> fig_, ax_ = metric.plot(values) r9r;r2r2r3r<'r=rr>r@rArBrCrrDrErrrrrFr rKstrrr4rrrrr<r2r2r2r3rIs"  d    rIc@rH)MultilabelPrecisionaCompute `Precision`_ for multilabel tasks. .. math:: \text{Precision} = \frac{\text{TP}}{\text{TP} + \text{FP}} Where :math:`\text{TP}` and :math:`\text{FP}` represent the number of true positives and false positives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FP} \neq 0`. If this case is encountered for any label, the metric for that label will be set to `zero_division` (0 or 1, default is 0) and the overall metric may therefore be affected in turn. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): An int tensor or float tensor of shape ``(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`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, C, ...)``. As output to ``forward`` and ``compute`` the metric returns the following output: - ``mlp`` (:class:`~torch.Tensor`): 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)`` If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present, which the reduction will then be applied over instead of the sample dimension ``N``. Args: 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. zero_division: Should be `0` or `1`. The value returned when :math:`\text{TP} + \text{FP} = 0`. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.classification import MultilabelPrecision >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0, 0, 1], [1, 0, 1]]) >>> metric = MultilabelPrecision(num_labels=3) >>> metric(preds, target) tensor(0.5000) >>> mlp = MultilabelPrecision(num_labels=3, average=None) >>> mlp(preds, target) tensor([1.0000, 0.0000, 0.5000]) Example (preds is float tensor): >>> from torchmetrics.classification import MultilabelPrecision >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]]) >>> metric = MultilabelPrecision(num_labels=3) >>> metric(preds, target) tensor(0.5000) >>> mlp = MultilabelPrecision(num_labels=3, average=None) >>> mlp(preds, target) tensor([1.0000, 0.0000, 0.5000]) Example (multidim tensors): >>> from torchmetrics.classification import MultilabelPrecision >>> 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]]]) >>> metric = MultilabelPrecision(num_labels=3, multidim_average='samplewise') >>> metric(preds, target) tensor([0.3333, 0.0000]) >>> mlp = MultilabelPrecision(num_labels=3, multidim_average='samplewise', average=None) >>> mlp(preds, target) tensor([[0.5000, 0.5000, 0.0000], [0.0000, 0.0000, 0.0000]]) FrTrrrrrr LabelrKr!c C0|\}}}}td|||||j|jd|jd S)r#r$Tr'r( multilabelr)r+r r'r(r)r,r2r2r3r4zMultilabelPrecision.computeNr6r7cCr8)ayPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure object and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting a single value >>> from torchmetrics.classification import MultilabelPrecision >>> metric = MultilabelPrecision(num_labels=3) >>> metric.update(randint(2, (20, 3)), randint(2, (20, 3))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting multiple values >>> from torchmetrics.classification import MultilabelPrecision >>> metric = MultilabelPrecision(num_labels=3) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(randint(2, (20, 3)), randint(2, (20, 3)))) >>> fig_, ax_ = metric.plot(values) r9r;r2r2r3r<r=rr>rQr2r2r2r3rSRs"  a    rSc@r) BinaryRecalla Compute `Recall`_ for binary tasks. .. math:: \text{Recall} = \frac{\text{TP}}{\text{TP} + \text{FN}} Where :math:`\text{TP}` and :math:`\text{FN}` represent the number of true positives and false negatives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FN} \neq 0`. If this case is encountered a score of `zero_division` (0 or 1, default is 0) is returned. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): An int tensor or float tensor of shape ``(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`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` As output to ``forward`` and ``compute`` the metric returns the following output: - ``br`` (:class:`~torch.Tensor`): 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. If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present, which the reduction will then be applied over instead of the sample dimension ``N``. Args: 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. zero_division: Should be `0` or `1`. The value returned when :math:`\text{TP} + \text{FN} = 0`. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.classification import BinaryRecall >>> target = tensor([0, 1, 0, 1, 0, 1]) >>> preds = tensor([0, 0, 1, 1, 0, 1]) >>> metric = BinaryRecall() >>> metric(preds, target) tensor(0.6667) Example (preds is float tensor): >>> from torchmetrics.classification import BinaryRecall >>> target = tensor([0, 1, 0, 1, 0, 1]) >>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92]) >>> metric = BinaryRecall() >>> metric(preds, target) tensor(0.6667) Example (multidim tensors): >>> from torchmetrics.classification import BinaryRecall >>> 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]]]) >>> metric = BinaryRecall(multidim_average='samplewise') >>> metric(preds, target) tensor([0.6667, 0.0000]) FrTrrrrrr r!c Cr")r#recallr%r&r*r,r2r2r3r4?r5zBinaryRecall.computeNr6r7cCr8)a)Plot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure object and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting a single value >>> from torchmetrics.classification import BinaryRecall >>> metric = BinaryRecall() >>> metric.update(rand(10), randint(2,(10,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting multiple values >>> from torchmetrics.classification import BinaryRecall >>> metric = BinaryRecall() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(rand(10), randint(2,(10,)))) >>> fig_, ax_ = metric.plot(values) r9r;r2r2r3r<Mr=rr>r?r2r2r2r3rZrGrZc@rH)MulticlassRecallaCompute `Recall`_ for multiclass tasks. .. math:: \text{Recall} = \frac{\text{TP}}{\text{TP} + \text{FN}} Where :math:`\text{TP}` and :math:`\text{FN}` represent the number of true positives and false negatives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FN} \neq 0`. If this case is encountered for any class, the metric for that class will be set to `zero_division` (0 or 1, default is 0) and the overall metric may therefore be affected in turn. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` or float tensor of shape ``(N, C, ..)`` If preds is a floating point we apply ``torch.argmax`` along the ``C`` dimension to automatically convert probabilities/logits into an int tensor. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` As output to ``forward`` and ``compute`` the metric returns the following output: - ``mcr`` (:class:`~torch.Tensor`): 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)`` If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present, which the reduction will then be applied over instead of the sample dimension ``N``. Args: 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. zero_division: Should be `0` or `1`. The value returned when :math:`\text{TP} + \text{FN} = 0`. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.classification import MulticlassRecall >>> target = tensor([2, 1, 0, 0]) >>> preds = tensor([2, 1, 0, 1]) >>> metric = MulticlassRecall(num_classes=3) >>> metric(preds, target) tensor(0.8333) >>> mcr = MulticlassRecall(num_classes=3, average=None) >>> mcr(preds, target) tensor([0.5000, 1.0000, 1.0000]) Example (preds is float tensor): >>> from torchmetrics.classification import MulticlassRecall >>> 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]]) >>> metric = MulticlassRecall(num_classes=3) >>> metric(preds, target) tensor(0.8333) >>> mcr = MulticlassRecall(num_classes=3, average=None) >>> mcr(preds, target) tensor([0.5000, 1.0000, 1.0000]) Example (multidim tensors): >>> from torchmetrics.classification import MulticlassRecall >>> 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]]]) >>> metric = MulticlassRecall(num_classes=3, multidim_average='samplewise') >>> metric(preds, target) tensor([0.5000, 0.2778]) >>> mcr = MulticlassRecall(num_classes=3, multidim_average='samplewise', average=None) >>> mcr(preds, target) tensor([[1.0000, 0.0000, 0.5000], [0.0000, 0.3333, 0.5000]]) FrTrrrrrr rJrKr!c CrL)r#r[rMrOr,r2r2r3r4rPzMulticlassRecall.computeNr6r7cCr8)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure object and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> from torch import randint >>> # Example plotting a single value per class >>> from torchmetrics.classification import MulticlassRecall >>> metric = MulticlassRecall(num_classes=3, average=None) >>> metric.update(randint(3, (20,)), randint(3, (20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import randint >>> # Example plotting a multiple values per class >>> from torchmetrics.classification import MulticlassRecall >>> metric = MulticlassRecall(num_classes=3, average=None) >>> values = [] >>> for _ in range(20): ... values.append(metric(randint(3, (20,)), randint(3, (20,)))) >>> fig_, ax_ = metric.plot(values) r9r;r2r2r3r<r=rr>rQr2r2r2r3r\xs"  c    r\c@rH)MultilabelRecalla#Compute `Recall`_ for multilabel tasks. .. math:: \text{Recall} = \frac{\text{TP}}{\text{TP} + \text{FN}} Where :math:`\text{TP}` and :math:`\text{FN}` represent the number of true positives and false negatives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FN} \neq 0`. If this case is encountered for any label, the metric for that label will be set to `zero_division` (0 or 1, default is 0) and the overall metric may therefore be affected in turn. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): An int or float tensor of shape ``(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`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, C, ...)`` As output to ``forward`` and ``compute`` the metric returns the following output: - ``mlr`` (:class:`~torch.Tensor`): 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)`` If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present, which the reduction will then be applied over instead of the sample dimension ``N``. Args: 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. zero_division: Should be `0` or `1`. The value returned when :math:`\text{TP} + \text{FN} = 0`. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.classification import MultilabelRecall >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0, 0, 1], [1, 0, 1]]) >>> metric = MultilabelRecall(num_labels=3) >>> metric(preds, target) tensor(0.6667) >>> mlr = MultilabelRecall(num_labels=3, average=None) >>> mlr(preds, target) tensor([1., 0., 1.]) Example (preds is float tensor): >>> from torchmetrics.classification import MultilabelRecall >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]]) >>> metric = MultilabelRecall(num_labels=3) >>> metric(preds, target) tensor(0.6667) >>> mlr = MultilabelRecall(num_labels=3, average=None) >>> mlr(preds, target) tensor([1., 0., 1.]) Example (multidim tensors): >>> from torchmetrics.classification import MultilabelRecall >>> 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]]]) >>> metric = MultilabelRecall(num_labels=3, multidim_average='samplewise') >>> metric(preds, target) tensor([0.6667, 0.0000]) >>> mlr = MultilabelRecall(num_labels=3, multidim_average='samplewise', average=None) >>> mlr(preds, target) tensor([[1., 1., 0.], [0., 0., 0.]]) FrTrrrrrr rTrKr!c CrU)r#r[TrVrXr,r2r2r3r4rYzMultilabelRecall.computeNr6r7cCr8)amPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure object and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting a single value >>> from torchmetrics.classification import MultilabelRecall >>> metric = MultilabelRecall(num_labels=3) >>> metric.update(randint(2, (20, 3)), randint(2, (20, 3))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import rand, randint >>> # Example plotting multiple values >>> from torchmetrics.classification import MultilabelRecall >>> metric = MultilabelRecall(num_labels=3) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(randint(2, (20, 3)), randint(2, (20, 3)))) >>> fig_, ax_ = metric.plot(values) r9r;r2r2r3r<r=rr>rQr2r2r2r3r]s"  `    r]c@eZdZdZ        ddedd ed d ed eed eedeeddeeddeedeede de de fddZ dS) PrecisionafCompute `Precision`_. .. math:: \text{Precision} = \frac{\text{TP}}{\text{TP} + \text{FP}} Where :math:`\text{TP}` and :math:`\text{FP}` represent the number of true positives and false positives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FP} \neq 0`. If this case is encountered for any class/label, the metric for that class/label will be set to 0 and the overall metric may therefore be affected in turn. 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'``, ``'multiclass'`` or ``'multilabel'``. See the documentation of :class:`~torchmetrics.classification.BinaryPrecision`, :class:`~torchmetrics.classification.MulticlassPrecision` and :class:`~torchmetrics.classification.MultilabelPrecision` for the specific details of each argument influence and examples. Legacy Example: >>> from torch import tensor >>> preds = tensor([2, 0, 2, 1]) >>> target = tensor([1, 1, 2, 0]) >>> precision = Precision(task="multiclass", average='macro', num_classes=3) >>> precision(preds, target) tensor(0.1667) >>> precision = Precision(task="multiclass", average='micro', num_classes=3) >>> precision(preds, target) tensor(0.2500) ?NmicroglobalTclstaskr% multiclassrW threshold num_classes num_labelsr'ramacroweightednoner(rb samplewiserN ignore_index validate_argskwargsr!c Ks|dusJ| ||| dt|}|tjkr!t|fi| S|tjkrNt|ts5tdt |dt|tsDtdt |dt |||fi| S|tj krlt|tsbtdt |dt |||fi| Std|d) Initialize task metric.Nr(rqrr+`num_classes` is expected to be `int` but ` was passed.`%`top_k` is expected to be `int` but `*`num_labels` is expected to be `int` but `zTask z not supported!) updaterfrom_strBINARYr MULTICLASS isinstanceint ValueErrortyperI MULTILABELrS rdrerhrirjr'r(rNrqrrrsr2r2r3__new__s(        zPrecision.__new__r`NNrarbrcNT r@rArBrCrrrFrrrDrr rr2r2r2r3r_F      r_c@r^)RecallaECompute `Recall`_. .. math:: \text{Recall} = \frac{\text{TP}}{\text{TP} + \text{FN}} Where :math:`\text{TP}` and :math:`\text{FN}` represent the number of true positives and false negatives respectively. The metric is only proper defined when :math:`\text{TP} + \text{FN} \neq 0`. If this case is encountered for any class/label, the metric for that class/label will be set to 0 and the overall metric may therefore be affected in turn. 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'``, ``'multiclass'`` or ``'multilabel'``. See the documentation of :class:`~torchmetrics.classification.BinaryRecall`, :class:`~torchmetrics.classification.MulticlassRecall` and :class:`~torchmetrics.classification.MultilabelRecall` for the specific details of each argument influence and examples. Legacy Example: >>> from torch import tensor >>> preds = tensor([2, 0, 2, 1]) >>> target = tensor([1, 1, 2, 0]) >>> recall = Recall(task="multiclass", average='macro', num_classes=3) >>> recall(preds, target) tensor(0.3333) >>> recall = Recall(task="multiclass", average='micro', num_classes=3) >>> recall(preds, target) tensor(0.2500) r`NrarbrcTrdrerfrhrirjr'rkr(rorNrqrrrsr!c Kst|}|dus J| ||| d|tjkr!t|fi| S|tjkrNt|ts5tdt |dt|tsDtdt |dt |||fi| S|tj krlt|tsbtdt |dt |||fi| SdS)rtNrurvrwrxry) rr{rzr|rZr}r~rrrr\rr]rr2r2r3rs(        zRecall.__new__rrr2r2r2r3rrrN)$collections.abcrtypingrrrtorchrtyping_extensionsr torchmetrics.classification.baser'torchmetrics.classification.stat_scoresr r r 7torchmetrics.functional.classification.precision_recallr torchmetrics.metricr torchmetrics.utilities.enumsrtorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rrIrSrZr\r]r_rr2r2r2r3s6         '$&#A