a  d6F@sddlmZmZmZmZddlZddlmZddlmZddl m Z ddl m Z m Z mZddlmZmZmZmZmZmZddlmZdd lmZdd lmZdd lmZdd lmZm Z esd dgZ!GdddeZ"GdddeZ#Gddde Z$dS))AnyOptionalSequenceUnionN)Tensor)Literal)_ClassificationTaskWrapper)_exact_match_reduce_multiclass_exact_match_update_multilabel_exact_match_update)&_multiclass_stat_scores_arg_validation_multiclass_stat_scores_format)_multiclass_stat_scores_tensor_validation&_multilabel_stat_scores_arg_validation_multilabel_stat_scores_format)_multilabel_stat_scores_tensor_validation)Metric) dim_zero_cat)ClassificationTaskNoBinary)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEMulticlassExactMatch.plotMultilabelExactMatch.plotcseZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <d Z e ed <deedeeeeddfdd ZeeddddZedddZdeeeeefeeedddZZS)MulticlassExactMatcha Compute Exact match (also known as subset accuracy) for multiclass tasks. Exact Match is a stricter version of accuracy where all labels have to match exactly for the sample to be correctly classified. 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: - ``mcem`` (:class:`~torch.Tensor`): A tensor whose returned shape depends on the ``multidim_average`` argument: - If ``multidim_average`` is set to ``global`` the output will be a scalar tensor - If ``multidim_average`` is set to ``samplewise`` the output will be a tensor of shape ``(N,)`` Args: num_classes: Integer specifing the number of labels 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. Example (multidim tensors): >>> from torch import tensor >>> from torchmetrics.classification import MulticlassExactMatch >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]]) >>> preds = tensor([[[0, 1], [2, 1], [0, 2]], [[2, 2], [2, 1], [1, 0]]]) >>> metric = MulticlassExactMatch(num_classes=3, multidim_average='global') >>> metric(preds, target) tensor(0.5000) Example (multidim tensors): >>> from torchmetrics.classification import MulticlassExactMatch >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]]) >>> preds = tensor([[[0, 1], [2, 1], [0, 2]], [[2, 2], [2, 1], [1, 0]]]) >>> metric = MulticlassExactMatch(num_classes=3, multidim_average='samplewise') >>> metric(preds, target) tensor([1., 0.]) Fis_differentiableThigher_is_betterfull_state_updateplot_lower_bound?plot_upper_boundZClassplot_legend_nameglobalNr# samplewise) num_classesmultidim_average ignore_index validate_argskwargsreturnc stjfi|d\}}|r.t|||||||_||_||_||_|jd|jdkrftj dtj dng|jdkrvdndd|jd tj dtj d|jdkrdnd ddS) N)Ncorrectr#r,ZdtypesumcatZdist_reduce_fxtotalmean) super__init__r r&r'r(r) add_statetorchzeroslong)selfr&r'r(r)r*Ztop_kaverage __class__p/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/classification/exact_match.pyr5hs$zMulticlassExactMatch.__init__predstargetr+cCs|jrt|||j|j|jt||d\}}t|||j|j\}}|jdkr`|j|||_ n|j|7_|j |7_ dS)z2Update metric states with predictions and targets.r,r%N) r)rr&r'r(r r r-appendr2r:rArBr-r2r>r>r?updates  zMulticlassExactMatch.updater+cCs(t|jtrt|jn|j}t||jSzCompute metric. isinstancer-listrr r2r:r-r>r>r?computeszMulticlassExactMatch.computevalaxr+cCs |||S)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 >>> # Example plotting a single value per class >>> from torch import randint >>> from torchmetrics.classification import MulticlassExactMatch >>> metric = MulticlassExactMatch(num_classes=3) >>> metric.update(randint(3, (20,5)), randint(3, (20,5))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import randint >>> # Example plotting a multiple values per class >>> from torchmetrics.classification import MulticlassExactMatch >>> metric = MulticlassExactMatch(num_classes=3) >>> values = [] >>> for _ in range(20): ... values.append(metric(randint(3, (20,5)), randint(3, (20,5)))) >>> fig_, ax_ = metric.plot(values) Z_plotr:rNrOr>r>r?plots(r)r#NT)NN__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatr!r"strintrrrr5rrErLrrrrrR __classcell__r>r>r<r?r,s2 4      rc seZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <d Z e ed <dee edeeeeddfdd ZeeddddZedddZdeeeeefeeedddZZS)MultilabelExactMatchah Compute Exact match (also known as subset accuracy) for multilabel tasks. Exact Match is a stricter version of accuracy where all labels have to match exactly for the sample to be correctly classified. 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. Addtionally, 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: - ``mlem`` (:class:`~torch.Tensor`): A tensor whose returned shape depends on the ``multidim_average`` argument: - If ``multidim_average`` is set to ``global`` the output will be a scalar tensor - If ``multidim_average`` is set to ``samplewise`` the output will be a tensor of shape ``(N,)`` Args: num_labels: Integer specifing the number of 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. Example (preds is int tensor): >>> from torch import tensor >>> from torchmetrics.classification import MultilabelExactMatch >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0, 0, 1], [1, 0, 1]]) >>> metric = MultilabelExactMatch(num_labels=3) >>> metric(preds, target) tensor(0.5000) Example (preds is float tensor): >>> from torchmetrics.classification import MultilabelExactMatch >>> target = tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]]) >>> metric = MultilabelExactMatch(num_labels=3) >>> metric(preds, target) tensor(0.5000) Example (multidim tensors): >>> from torchmetrics.classification import MultilabelExactMatch >>> 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 = MultilabelExactMatch(num_labels=3, multidim_average='samplewise') >>> metric(preds, target) tensor([0., 0.]) FrTrrrrr r!ZLabelr"?r#Nr$) num_labels thresholdr'r(r)r*r+c stjfi||r(t||d||d||_||_||_||_||_|jd|jdkrft j dt j dng|jdkrvdndd|jd t j dt j d|jdkrdnd ddS) N)r;r'r(r-r#r,r.r/r0r1r2r3) r4r5rr`rar'r(r)r6r7r8r9)r:r`rar'r(r)r*r<r>r?r5 s(  zMultilabelExactMatch.__init__r@cCs|jrt|||j|j|jt|||j|j|j\}}t|||j|j\}}|jdkrj|j |||_ n|j|7_|j |7_ dS)z*Update state with predictions and targets.r%N) r)rr`r'r(rrar r-rCr2rDr>r>r?rE*s  zMultilabelExactMatch.updaterFcCs(t|jtrt|jn|j}t||jSrGrHrKr>r>r?rL;szMultilabelExactMatch.computerMcCs |||S)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 and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> from torch import rand, randint >>> from torchmetrics.classification import MultilabelExactMatch >>> metric = MultilabelExactMatch(num_labels=3) >>> metric.update(randint(2, (20, 3, 5)), randint(2, (20, 3, 5))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torch import rand, randint >>> from torchmetrics.classification import MultilabelExactMatch >>> metric = MultilabelExactMatch(num_labels=3) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(randint(2, (20, 3, 5)), randint(2, (20, 3, 5)))) >>> fig_, ax_ = metric.plot(values) rPrQr>r>r?rR@s(r)r_r#NT)NNrSr>r>r<r?r^s6 ?      r^c @sDeZdZdZd edeeeeeedeeee e d d d Z dS) ExactMatchaCompute Exact match (also known as subset accuracy). Exact Match is a stricter version of accuracy where all labels have to match exactly for the sample to be correctly classified. This module is a simple wrapper to get the task specific versions of this metric, which is done by setting the ``task`` argument to either ``'multiclass'`` or ``multilabel``. See the documentation of :class:`~torchmetrics.classification.MulticlassExactMatch` and :class:`~torchmetrics.classification.MultilabelExactMatch` for the specific details of each argument influence and examples. Legacy Example: >>> from torch import tensor >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]]) >>> preds = tensor([[[0, 1], [2, 1], [0, 2]], [[2, 2], [2, 1], [1, 0]]]) >>> metric = ExactMatch(task="multiclass", num_classes=3, multidim_average='global') >>> metric(preds, target) tensor(0.5000) >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]]) >>> preds = tensor([[[0, 1], [2, 1], [0, 2]], [[2, 2], [2, 1], [1, 0]]]) >>> metric = ExactMatch(task="multiclass", num_classes=3, multidim_average='samplewise') >>> metric(preds, target) tensor([1., 0.]) r_Nr#T)binaryZ multiclassZ multilabelr$) taskrar&r`r'r(r)r*r+c Kst|}||||d|tjkrTt|tsDtdt|dt|fi|S|tj krt|ts|tdt|dt ||fi|Std|ddS)zInitialize task metric.)r'r(r)z+`num_classes` is expected to be `int` but `z was passed.`z*`num_labels` is expected to be `int` but `zTask z not supported!N) rZfrom_strrEZ MULTICLASSrIr\ ValueErrortyperZ MULTILABELr^) clsrdrar&r`r'r(r)r*r>r>r?__new__s      zExactMatch.__new__)r_NNr#NT) rTrUrVrWrrZrr\rXrrrhr>r>r>r?rbks$rb)%typingrrrrr7rZtyping_extensionsrZ torchmetrics.classification.baserZ2torchmetrics.functional.classification.exact_matchr r r Z2torchmetrics.functional.classification.stat_scoresr r rrrrZtorchmetrics.metricrZtorchmetrics.utilities.datarZtorchmetrics.utilities.enumsrZtorchmetrics.utilities.importsrZtorchmetrics.utilities.plotrrZ__doctest_skip__rr^rbr>r>r>r?s$        (