# SOME DESCRIPTIVE TITLE. # Copyright (C) 2021, PaddleNLP # This file is distributed under the same license as the PaddleNLP package. # FIRST AUTHOR , 2022. # #, fuzzy msgid "" msgstr "" "Project-Id-Version: PaddleNLP \n" "Report-Msgid-Bugs-To: \n" "POT-Creation-Date: 2022-03-18 21:31+0800\n" "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" "Last-Translator: FULL NAME \n" "Language-Team: LANGUAGE \n" "MIME-Version: 1.0\n" "Content-Type: text/plain; charset=utf-8\n" "Content-Transfer-Encoding: 8bit\n" "Generated-By: Babel 2.9.0\n" #: ../source/paddlenlp.metrics.glue.rst:2 msgid "glue" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1:1 paddlenlp.metrics.glue.Mcc:1 #: paddlenlp.metrics.glue.MultiLabelsMetric:1 #: paddlenlp.metrics.glue.PearsonAndSpearman:1 msgid "基类：:class:`paddle.metric.metrics.Metric`" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1:1 msgid "" "This class encapsulates Accuracy, Precision, Recall and F1 metric logic, " "and `accumulate` function returns accuracy, precision, recall and f1. The" " overview of all metrics could be seen at the document of `paddle.metric " "`_" " for details." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1 #: paddlenlp.metrics.glue.AccuracyAndF1.compute #: paddlenlp.metrics.glue.AccuracyAndF1.update paddlenlp.metrics.glue.Mcc #: paddlenlp.metrics.glue.Mcc.compute paddlenlp.metrics.glue.Mcc.update #: paddlenlp.metrics.glue.MultiLabelsMetric #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate #: paddlenlp.metrics.glue.MultiLabelsMetric.compute #: paddlenlp.metrics.glue.MultiLabelsMetric.update #: paddlenlp.metrics.glue.PearsonAndSpearman #: paddlenlp.metrics.glue.PearsonAndSpearman.update msgid "参数" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1:7 msgid "" "Number of top elements to look at for computing accuracy. Defaults to " "(1,)." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1:10 msgid "The positive label for calculating precision and recall. Defaults to 1." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1:14 msgid "String name of the metric instance. Defaults to 'acc_and_f1'." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1:18 paddlenlp.metrics.glue.Mcc:7 #: paddlenlp.metrics.glue.MultiLabelsMetric:11 #: paddlenlp.metrics.glue.PearsonAndSpearman:9 msgid "示例" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.compute:1 #: paddlenlp.metrics.glue.MultiLabelsMetric.compute:1 msgid "" "Accepts network's output and the labels, and calculates the top-k " "(maximum value in topk) indices for accuracy." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.compute:4 msgid "" "Predicted tensor, and its dtype is float32 or float64, and has a shape of" " [batch_size, num_classes]." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.compute:7 msgid "" "The ground truth tensor, and its dtype is int64, and has a shape of " "[batch_size, 1] or [batch_size, num_classes] in one hot representation." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate #: paddlenlp.metrics.glue.AccuracyAndF1.compute #: paddlenlp.metrics.glue.AccuracyAndF1.name #: paddlenlp.metrics.glue.Mcc.accumulate paddlenlp.metrics.glue.Mcc.compute #: paddlenlp.metrics.glue.Mcc.name #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate #: paddlenlp.metrics.glue.MultiLabelsMetric.compute #: paddlenlp.metrics.glue.MultiLabelsMetric.name #: paddlenlp.metrics.glue.PearsonAndSpearman.accumulate #: paddlenlp.metrics.glue.PearsonAndSpearman.name msgid "返回" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.compute:12 msgid "" "Correct mask, each element indicates whether the prediction equals to the" " label. Its' a tensor with a data type of float32 and has a shape of " "[batch_size, topk]." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate #: paddlenlp.metrics.glue.AccuracyAndF1.compute #: paddlenlp.metrics.glue.AccuracyAndF1.name #: paddlenlp.metrics.glue.Mcc.accumulate paddlenlp.metrics.glue.Mcc.compute #: paddlenlp.metrics.glue.Mcc.name #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate #: paddlenlp.metrics.glue.MultiLabelsMetric.compute #: paddlenlp.metrics.glue.MultiLabelsMetric.name #: paddlenlp.metrics.glue.PearsonAndSpearman.accumulate #: paddlenlp.metrics.glue.PearsonAndSpearman.name msgid "返回类型" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.update:1 #: paddlenlp.metrics.glue.MultiLabelsMetric.update:1 msgid "" "Updates the metrics states (accuracy, precision and recall), in order to " "calculate accumulated accuracy, precision and recall of all instances." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.update:4 msgid "" "Correct mask for calculating accuracy, and it's a tensor with shape " "[batch_size, topk] and has a dtype of float32." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:1 #: paddlenlp.metrics.glue.Mcc.accumulate:1 #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:1 #: paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:1 msgid "Calculates and returns the accumulated metric." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:3 msgid "" "The accumulated metric. A tuple of shape (acc, precision, recall, f1, " "average_of_acc_and_f1) With the fields: - `acc` (numpy.float64): " "The accumulated accuracy. - `precision` (numpy.float64): The " "accumulated precision. - `recall` (numpy.float64): The accumulated " "recall. - `f1` (numpy.float64): The accumulated f1. - " "`average_of_acc_and_f1` (numpy.float64): The average of accumulated " "accuracy and f1." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:3 msgid "" "The accumulated metric. A tuple of shape (acc, precision, recall, f1, " "average_of_acc_and_f1)" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:6 #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:27 #: paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:6 msgid "With the fields:" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:8 msgid "`acc` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:9 msgid "The accumulated accuracy." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:10 msgid "`precision` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:11 #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:30 msgid "The accumulated precision." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:12 msgid "`recall` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:13 #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:32 msgid "The accumulated recall." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:14 msgid "`f1` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:15 #: paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:34 msgid "The accumulated f1." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:16 msgid "`average_of_acc_and_f1` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.accumulate:17 msgid "The average of accumulated accuracy and f1." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.reset:1 #: paddlenlp.metrics.glue.Mcc.reset:1 #: paddlenlp.metrics.glue.PearsonAndSpearman.reset:1 msgid "Resets all metric states." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.name:1 #: paddlenlp.metrics.glue.Mcc.name:1 #: paddlenlp.metrics.glue.MultiLabelsMetric.name:1 #: paddlenlp.metrics.glue.PearsonAndSpearman.name:1 msgid "Returns name of the metric instance." msgstr "" #: of paddlenlp.metrics.glue.AccuracyAndF1.name:3 #: paddlenlp.metrics.glue.Mcc.name:3 #: paddlenlp.metrics.glue.MultiLabelsMetric.name:3 #: paddlenlp.metrics.glue.PearsonAndSpearman.name:3 msgid "The name of the metric instance." msgstr "" #: of paddlenlp.metrics.glue.Mcc:1 msgid "" "This class calculates `Matthews correlation coefficient " "`_ ." msgstr "" #: of paddlenlp.metrics.glue.Mcc:3 msgid "String name of the metric instance. Defaults to 'mcc'." msgstr "" #: of paddlenlp.metrics.glue.Mcc.compute:1 msgid "" "Processes the pred tensor, and returns the indices of the maximum of each" " sample." msgstr "" #: of paddlenlp.metrics.glue.Mcc.compute:4 msgid "" "The predicted value is a Tensor with dtype float32 or float64. Shape is " "[batch_size, 1]." msgstr "" #: of paddlenlp.metrics.glue.Mcc.compute:7 msgid "" "The ground truth value is Tensor with dtype int64, and its shape is " "[batch_size, 1]." msgstr "" #: of paddlenlp.metrics.glue.Mcc.compute:11 msgid "" "A tuple of preds and label. Each shape is [batch_size, 1], with dtype " "float32 or float64." msgstr "" #: of paddlenlp.metrics.glue.Mcc.update:1 msgid "" "Calculates states, i.e. the number of true positive, false positive, true" " negative and false negative samples." msgstr "" #: of paddlenlp.metrics.glue.Mcc.update:4 msgid "" "Tuple of predicted value and the ground truth label, with dtype float32 " "or float64. Each shape is [batch_size, 1]." msgstr "" #: of paddlenlp.metrics.glue.Mcc.accumulate:3 msgid "" "Returns the accumulated metric, a tuple of shape (mcc,), `mcc` is the " "accumulated mcc and its data type is float64." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman:1 #, python-format msgid "" "The class calculates `Pearson correlation coefficient " "`_ and " "`Spearman's rank correlation coefficient " "`_" " ." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman:5 msgid "String name of the metric instance. Defaults to 'pearson_and_spearman'." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.update:1 msgid "" "Ensures the type of preds and labels is numpy.ndarray and reshapes them " "into [-1, 1]." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.update:4 msgid "" "Tuple or list of predicted value and the ground truth label. Its data " "type should be float32 or float64 and its shape is [batch_size, d0, ..., " "dN]." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:3 msgid "" "Returns the accumulated metric, a tuple of (pearson, spearman, " "the_average_of_pearson_and_spearman). With the fields: - `pearson` " "(numpy.float64): The accumulated pearson. - `spearman` " "(numpy.float64): The accumulated spearman. - " "`the_average_of_pearson_and_spearman` (numpy.float64): The average of" " accumulated pearson and spearman correlation coefficient." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:3 msgid "" "Returns the accumulated metric, a tuple of (pearson, spearman, " "the_average_of_pearson_and_spearman)." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:9 msgid "`pearson` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:9 msgid "The accumulated pearson." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:12 msgid "`spearman` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:12 msgid "The accumulated spearman." msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:15 msgid "`the_average_of_pearson_and_spearman` (numpy.float64):" msgstr "" #: of paddlenlp.metrics.glue.PearsonAndSpearman.accumulate:15 msgid "The average of accumulated pearson and spearman correlation coefficient." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric:1 msgid "" "This class encapsulates Accuracy, Precision, Recall and F1 metric logic " "in multi-labels setting (also the binary setting). Some codes are taken " "and modified from sklearn.metrics ." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric:5 msgid "The total number of labels which is usually the number of classes" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric:7 msgid "String name of the metric instance. Defaults to 'multi_labels_metric'." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric:43 msgid "" "Note: When zero_division is encountered (details as followed), the " "corresponding metrics will be set to 0.0" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric:40 msgid "" "precision is zero_division if there are no positive predictions recall is" " zero_division if there are no positive labels fscore is zero_division if" " all labels AND predictions are negative" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.update:4 msgid "the tuple returned from `compute` function" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:9 msgid "Only report results for the class specified by pos_label." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:10 msgid "" "Calculate metrics globally by counting the total true positives, false " "negatives and false positives." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:12 msgid "" "Calculate metrics for each label, and find their unweighted mean. This " "does not take label imbalance into account." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:14 msgid "" "Calculate metrics for each label, and find their average weighted by " "support (the number of true instances for each label). This alters " "`macro` to account for label imbalance; it can result in an F-score that " "is not between precision and recall." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:18 msgid "" "The positive label for calculating precision and recall in binary " "settings. Noted: Only when `average='binary'`, this arguments will be " "used. Otherwise, it will be ignored. Defaults to 1." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:24 msgid "" "The accumulated metric. A tuple of shape (precision, recall, f1) With" " the fields: - `precision` (numpy.float64 or numpy.ndarray if " "average=None): The accumulated precision. - `recall` " "(numpy.float64 or numpy.ndarray if average=None): The accumulated" " recall. - `f1` (numpy.float64 or numpy.ndarray if average=None):" " The accumulated f1." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:33 msgid "The accumulated metric. A tuple of shape (precision, recall, f1)" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:29 msgid "`precision` (numpy.float64 or numpy.ndarray if average=None):" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:31 msgid "`recall` (numpy.float64 or numpy.ndarray if average=None):" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.accumulate:33 msgid "`f1` (numpy.float64 or numpy.ndarray if average=None):" msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.compute:4 msgid "" "Predicted tensor, and its dtype is float32 or float64, and has a shape of" " [batch_size, *, num_labels]." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.compute:7 msgid "" "The ground truth tensor, and its dtype is int64, and has a shape of " "[batch_size, *] or [batch_size, *, num_labels] in one hot representation." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.compute:12 msgid "" "it contains two Tensor of shape [*, 1]. The tuple should be passed to " "`update` function." msgstr "" #: of paddlenlp.metrics.glue.MultiLabelsMetric.reset:1 msgid "Reset states and result" msgstr ""