a  d@sddlmZmZmZmZmZddlmZmZddl m Z m Z ddl m Z ddlmZddlmZmZesndgZGdd d e Zd S) )AnyDictOptionalSequenceUnion)Tensortensor)_perplexity_compute_perplexity_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEPerplexity.plotcseZdZUdZdZdZdZeed<eed<de e e e e fddfdd Zeedd d d Zed ddZde eeeefe eedddZZS) PerplexityaPerplexity 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 torchmetrics.text import Perplexity >>> import torch >>> gen = torch.manual_seed(42) >>> preds = torch.rand(2, 8, 5, generator=gen) >>> target = torch.randint(5, (2, 8), generator=gen) >>> target[0, 6:] = -100 >>> perp = Perplexity(ignore_index=-100) >>> perp(preds, target) tensor(5.8540) TFtotal_log_probscountN) ignore_indexkwargsreturnc sdtjfi||dur2t|ts2td|||_|jdtddd|jdtddddS)NzIArgument `ignore_index` expected to either be `None` or an `int` but got rgsum)defaultZdist_reduce_fxr)super__init__ isinstanceint ValueErrorrZ add_stater)selfrr __class__e/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/text/perplexity.pyrDs zPerplexity.__init__)predstargetrcCs2t|||j\}}|j|7_|j|7_dS)z*Update state with predictions and targets.N)r rrr)rr"r#rrr r r!updatePszPerplexity.update)rcCst|j|jS)zCompute the Perplexity.)r rr)rr r r!computeVszPerplexity.compute)valaxrcCs |||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) )Z_plot)rr&r'r r r!plotZs(r)N)NN)__name__ __module__ __qualname____doc__Zis_differentiableZhigher_is_betterZfull_state_updater__annotations__rrrstrrrr$r%rrr rr( __classcell__r r rr!rs& !  rN)typingrrrrrZtorchrrZ'torchmetrics.functional.text.perplexityr r Ztorchmetrics.metricr Ztorchmetrics.utilities.importsr Ztorchmetrics.utilities.plotr rZ__doctest_skip__rr r r r!s