o .wi@sddlmZddlmZmZmZddlmZmZddl m Z m Z ddl m Z ddlmZddlmZmZes9dgZGd d d e Zd S) )Sequence)AnyOptionalUnion)Tensortensor)_perplexity_compute_perplexity_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEPerplexity.plotcseZdZUdZdZdZdZeed<eed< dde e de e e fd dffd d Zd ed ed dfddZd efddZ dde eeeefde ed efddZZS) PerplexityaSPerplexity measures how well a language model predicts a text sample. It's calculated as the average number of bits per word a model needs to represent the sample. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): Logits or a unnormalized score assigned to each token in a sequence with shape [batch_size, seq_len, vocab_size], which is the output of a language model. Scores will be normalized internally using softmax. - ``target`` (:class:`~torch.Tensor`): Ground truth values with a shape [batch_size, seq_len] As output of ``forward`` and ``compute`` the metric returns the following output: - ``perp`` (:class:`~torch.Tensor`): A tensor with the perplexity score Args: ignore_index: Integer specifying a target class to ignore. If given, this class index does not contribute to the returned score. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Examples: >>> from torch import rand, randint >>> from torchmetrics.text import Perplexity >>> preds = rand(2, 8, 5) >>> target = randint(5, (2, 8)) >>> target[0, 6:] = -100 >>> perp = Perplexity(ignore_index=-100) >>> perp(preds, target) tensor(5.8540) TFtotal_log_probscountN ignore_indexkwargsreturnc sdtjdi||durt|tstd|||_|jdtddd|jdtddddS)NzIArgument `ignore_index` expected to either be `None` or an `int` but got rgsum)defaultdist_reduce_fxr)super__init__ isinstanceint ValueErrorr add_stater)selfrr __class__rY/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/text/perplexity.pyrEs zPerplexity.__init__predstargetcCs2t|||j\}}|j|7_|j|7_dS)z*Update state with predictions and targets.N)r rrr)rr#r$rrrrr"updateQszPerplexity.updatecCst|j|jS)zCompute the Perplexity.)rrr)rrrr"computeWszPerplexity.computevalaxcCs |||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.text import Perplexity >>> metric = Perplexity() >>> metric.update(torch.rand(2, 8, 5), torch.randint(5, (2, 8))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.text import Perplexity >>> metric = Perplexity() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(2, 8, 5), torch.randint(5, (2, 8)))) >>> fig_, ax_ = metric.plot(values) )_plot)rr'r(rrr"plot[s (r)N)NN)__name__ __module__ __qualname____doc__is_differentiablehigher_is_betterfull_state_updater__annotations__rrdictstrrrr%r&rrr r r* __classcell__rrr r"rs2 !  rN)collections.abcrtypingrrrtorchrr'torchmetrics.functional.text.perplexityrr torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotr r __doctest_skip__rrrrr"s