a  d@sddlmZmZmZmZddlZddlmZmZddlm Z ddl m Z m Z m Z ddlmZddlmZmZesvdgZGd d d e ZdS) )AnyOptionalSequenceUnionN)Tensortensor)Metric)_bleu_score_compute_bleu_score_update _tokenize_fn)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEBLEUScore.plotcseZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e ed <e ed <e ed <e ed<de eeee eddfdd ZeeeeeddddZe dddZdeee ee feeedddZZS) BLEUScoreaCalculate `BLEU score`_ of machine translated text with one or more references. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~Sequence`): An iterable of machine translated corpus - ``target`` (:class:`~Sequence`): An iterable of iterables of reference corpus As output of ``forward`` and ``update`` the metric returns the following output: - ``bleu`` (:class:`~torch.Tensor`): A tensor with the BLEU Score Args: n_gram: Gram value ranged from 1 to 4 smooth: Whether or not to apply smoothing, see `Machine Translation Evolution`_ kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. weights: Weights used for unigrams, bigrams, etc. to calculate BLEU score. If not provided, uniform weights are used. Raises: ValueError: If a length of a list of weights is not ``None`` and not equal to ``n_gram``. Example: >>> from torchmetrics.text import BLEUScore >>> preds = ['the cat is on the mat'] >>> target = [['there is a cat on the mat', 'a cat is on the mat']] >>> bleu = BLEUScore() >>> bleu(preds, target) tensor(0.7598) Fis_differentiableThigher_is_betterfull_state_updateplot_lower_bound?plot_upper_bound preds_len target_len numerator denominatorN)n_gramsmoothweightskwargsreturnc stjfi|||_||_|durJt||krJtdt|d||durV|n d|g||_|jdtddd|jdtddd|jd t |jdd|jd t |jdddS) Nz5List of weights has different weights than `n_gram`: z != rrrsum)Zdist_reduce_fxrrr) super__init__rrlen ValueErrorrZ add_statertorchzeros)selfrrrr  __class___/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/text/bleu.pyr$MszBLEUScore.__init__)predstargetr!c Cs,t|||j|j|j|j|jt\|_|_dS)z*Update state with predictions and targets.N)r rrrrrr )r)r.r/r,r,r-update`szBLEUScore.update)r!cCs"t|j|j|j|j|j|j|jS)zCalculate BLEU score.)r rrrrrrr)r)r,r,r-computemszBLEUScore.compute)valaxr!cCs |||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> from torchmetrics.text import BLEUScore >>> metric = BLEUScore() >>> preds = ['the cat is on the mat'] >>> target = [['there is a cat on the mat', 'a cat is on the mat']] >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torchmetrics.text import BLEUScore >>> metric = BLEUScore() >>> preds = ['the cat is on the mat'] >>> target = [['there is a cat on the mat', 'a cat is on the mat']] >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )Z_plot)r)r2r3r,r,r-plotss*r)rFN)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrintrrrr$strr0r1rr rr4 __classcell__r,r,r*r-r!s6        r)typingrrrrr'rrZ torchmetricsrZ!torchmetrics.functional.text.bleur r r Ztorchmetrics.utilities.importsr Ztorchmetrics.utilities.plotr rZ__doctest_skip__rr,r,r,r-s