:jvddlmZddlmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z mZddlmZe sd gZGd d eZy) )Sequence)AnyOptionalUnionN)Tensor)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE) WrapperMetriczMinMaxMetric.plotceZdZUdZdZeeed<eed<eed<de de dd ffd Z d e de dd fd Z de eeffd Zd e de de ffd Zdfd ZedeeefdefdZ ddeeeeefdeedefdZxZS) MinMaxMetricakWrapper metric that tracks both the minimum and maximum of a scalar/tensor across an experiment. The min/max value will be updated each time ``.compute`` is called. Args: base_metric: The metric of which you want to keep track of its maximum and minimum values. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError If ``base_metric` argument is not a subclasses instance of ``torchmetrics.Metric`` Example:: >>> import torch >>> from torchmetrics.wrappers import MinMaxMetric >>> from torchmetrics.classification import BinaryAccuracy >>> from pprint import pprint >>> base_metric = BinaryAccuracy() >>> minmax_metric = MinMaxMetric(base_metric) >>> preds_1 = torch.Tensor([[0.1, 0.9], [0.2, 0.8]]) >>> preds_2 = torch.Tensor([[0.9, 0.1], [0.2, 0.8]]) >>> labels = torch.Tensor([[0, 1], [0, 1]]).long() >>> pprint(minmax_metric(preds_1, labels)) {'max': tensor(1.), 'min': tensor(1.), 'raw': tensor(1.)} >>> pprint(minmax_metric.compute()) {'max': tensor(1.), 'min': tensor(1.), 'raw': tensor(1.)} >>> minmax_metric.update(preds_2, labels) >>> pprint(minmax_metric.compute()) {'max': tensor(1.), 'min': tensor(0.7500), 'raw': tensor(0.7500)} Tfull_state_updatemin_valmax_val base_metrickwargsreturnNc t|di|t|tst d|||_t jtd|_ t jtd|_ y)NzMExpected base metric to be an instance of `torchmetrics.Metric` but received infz-inf) super__init__ isinstancer ValueError _base_metrictorchtensorfloatrr)selfrr __class__s q/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/wrappers/minmax.pyrzMinMaxMetric.__init__Dsj "6"+v._`k_lm (||E%L1 ||E&M2 argsc<|jj|i|y)zUpdate the underlying metric.N)rupdate)r r$rs r"r&zMinMaxMetric.updateRs   $1&1r#c|jj}|j|std|d|jj |j |kr|n$|jj |j |_|jj |j |kDr|n$|jj |j |_||j|jdS)zCompute the underlying metric as well as max and min values for this metric. Returns a dictionary that consists of the computed value (``raw``), as well as the minimum (``min``) and maximum (``max``) values. zLReturned value from base metric should be a float or scalar tensor, but got .)rawmaxmin)rcompute_is_suitable_val RuntimeErrorrtodevicer)r vals r"r,zMinMaxMetric.computeVs'')$$S)!mnqmrrstu u"lloocjj9C?sT\\__UXU_U_E` "lloocjj9C?sT\\__UXU_U_E` 4<< EEr#c*tt| |i|S)z9Use the original forward method of the base metric class.)rr forward)r r$rr!s r"r3zMinMaxMetric.forwardds]D14B6BBr#cVt||jjy)zXSet ``max_val`` and ``min_val`` to the initialization bounds and resets the base metric.N)rresetr)r r!s r"r5zMinMaxMetric.reseths   !r#r1cxt|ttfryt|tr|j dk(Sy)z(Check whether min/max is a scalar value.TF)rintrrnumel)r1s r"r-zMinMaxMetric._is_suitable_valms3 cC< ( c6 "99;!# #r#axc&|j||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 >>> import torch >>> from torchmetrics.wrappers import MinMaxMetric >>> from torchmetrics.classification import BinaryAccuracy >>> metric = MinMaxMetric(BinaryAccuracy()) >>> metric.update(torch.randint(2, (20,)), torch.randint(2, (20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.wrappers import MinMaxMetric >>> from torchmetrics.classification import BinaryAccuracy >>> metric = MinMaxMetric(BinaryAccuracy()) >>> values = [ ] >>> for _ in range(3): ... values.append(metric(torch.randint(2, (20,)), torch.randint(2, (20,)))) >>> fig_, ax_ = metric.plot(values) )_plot)r r1r:s r"plotzMinMaxMetric.plotvsTzz#r""r#)rN)NN)__name__ __module__ __qualname____doc__rrbool__annotations__rrrrr&dictstrr,r3r5 staticmethodrrr-rr r r= __classcell__)r!s@r"rrsB)-x~, O O 3 3 3  32C23242 Fc6k* FCSCCCCC" eE6M2t_c*#E&(6*:":;<*#IQRZI[*# *#r#r)collections.abcrtypingrrrrrtorchmetrics.metricrtorchmetrics.utilities.importsr torchmetrics.utilities.plotr r torchmetrics.wrappers.abstractr __doctest_skip__rrr#r"rOs<%'' &@@8+,B#=B#r#