paddlenlp.datasets.dataset.po

# SOME DESCRIPTIVE TITLE.
# Copyright (C) 2021, PaddleNLP
# This file is distributed under the same license as the PaddleNLP package.
# FIRST AUTHOR <EMAIL@ADDRESS>, 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 <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <LL@li.org>\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.datasets.dataset.rst:2
msgid "dataset"
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset:1
msgid ""
"Wraps a map-style dataset-like object as an instance of `MapDataset`, and"
" equips it with `map` and other utility methods. All non-magic methods of"
" the raw object are also accessible."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read
#: paddlenlp.datasets.dataset.IterDataset
#: paddlenlp.datasets.dataset.IterDataset.filter
#: paddlenlp.datasets.dataset.IterDataset.map
#: paddlenlp.datasets.dataset.IterDataset.shard
#: paddlenlp.datasets.dataset.MapDataset
#: paddlenlp.datasets.dataset.MapDataset.filter
#: paddlenlp.datasets.dataset.MapDataset.map
#: paddlenlp.datasets.dataset.load_dataset
msgid "参数"
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset:5
msgid ""
"An object with `__getitem__` and `__len__` methods. It could be a list or"
" a subclass of `paddle.io.Dataset`."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset:8
#: paddlenlp.datasets.dataset.MapDataset:8
msgid "Other information to be passed to the dataset."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset:11
#: paddlenlp.datasets.dataset.MapDataset:11
msgid ""
"For examples of this class, please see `dataset_self_defined "
"<https://paddlenlp.readthedocs.io/zh/latest/data_prepare/dataset_self_defined.html>`__."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset.filter:1
#: paddlenlp.datasets.dataset.MapDataset.filter:1
msgid ""
"Filters samples by the filter function and uses the filtered data to "
"update this dataset."
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset.filter:4
msgid ""
"A filter function that takes a sample as input and returns a boolean. "
"Samples that return False would be discarded."
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset.filter:7
msgid ""
"Number of processes for multiprocessing. If set to 0, it doesn't use "
"multiprocessing. Defaults to `0`."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset.map:1
#: paddlenlp.datasets.dataset.MapDataset.map:1
msgid ""
"Performs specific function on the dataset to transform and update every "
"sample."
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset.map:3
msgid ""
"Transformations to be performed. It receives single sample as argument if"
" batched is False. Else it receives all examples."
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset.map:6
msgid ""
"If True, transformations would be delayed and performed on demand. "
"Otherwise, transforms all samples at once. Note that if `fn` is "
"stochastic, `lazy` should be True or you will get the same result on all "
"epochs. Defaults to False."
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset.map:11
msgid ""
"If True, transformations would take all examples as input and return a "
"collection of transformed examples. Note that if set True, `lazy` option "
"would be ignored. Defaults to False."
msgstr ""

#: of paddlenlp.datasets.dataset.MapDataset.map:15
msgid ""
"Number of processes for multiprocessing. If set to 0, it doesn't use "
"multiprocessing. Note that if set to positive value, `lazy` option would "
"be ignored. Defaults to 0."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder:1
msgid ""
"A base class for all DatasetBuilder. It provides a `read()` function to "
"turn a data file into a MapDataset or IterDataset."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder:4
msgid ""
"`_get_data()` function and `_read()` function should be implemented to "
"download data file and read data file into a `Iterable` of the examples."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder:7
msgid ""
"For how to define a custom `DatasetBuilder`, please see "
"`contribute_dataset "
"<https://paddlenlp.readthedocs.io/zh/latest/community/contribute_dataset.html>`__."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read:1
msgid ""
"Returns a dataset containing all the examples that can be read from the "
"file path."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read:3
msgid ""
"If `self.lazy` is False, this eagerly reads all instances from "
"`self._read()` and returns a `MapDataset`."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read:6
msgid ""
"If `self.lazy` is True, this returns an `IterDataset`, which internally "
"relies on the generator created from `self._read()` to lazily produce "
"examples. In this case your implementation of `_read()` must also be lazy"
" (that is, not load all examples into memory at once)."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read:11
msgid "Path of data file to read, usually provided by `_get_data` function."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read:14
msgid ""
"The split name of selected dataset. This only makes a different when data"
" files of different splits have different structures."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read
#: paddlenlp.datasets.dataset.load_dataset
msgid "返回"
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.read:18
msgid "A `MapDataset|IterDataset`."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.get_labels:1
msgid "Returns list of class labels of the dataset if specified."
msgstr ""

#: of paddlenlp.datasets.dataset.DatasetBuilder.get_vocab:1
msgid "Returns vocab file path of the dataset if specified."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset:1
msgid ""
"Wraps a dataset-like object as an instance of `IterDataset`, and equips "
"it with `map` and other utility methods. All non-magic methods of the raw"
" object also accessible."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset:5
msgid ""
"An object with `__iter__` function. It can be a Iterable or a subclass of"
" `paddle.io.IterableDataset`."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset.filter:4
msgid ""
"A filter function that takes a sample as input and returns a boolean. "
"Samples that return False are discarded."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset.shard:1
msgid "Split the dataset into `num_shards` pieces."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset.shard:3
msgid ""
"An integer representing the number of data shards. If None, `num_shards` "
"would be number of trainers. Defaults to None."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset.shard:7
msgid ""
"An integer representing the index of the current shard. If None, `index` "
"would be the current trainer rank id. Defaults to None."
msgstr ""

#: of paddlenlp.datasets.dataset.IterDataset.map:3
msgid "Transformations to be performed. It receives single sample as argument."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:1
msgid ""
"This method will load a dataset, either form PaddleNLP library or from a "
"self-defined data loading script, by calling functions in "
"`DatasetBuilder`."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:4
msgid ""
"For all the names of datasets in PaddleNLP library, see here:  "
"`dataset_list "
"<https://paddlenlp.readthedocs.io/zh/latest/data_prepare/dataset_list.html>`__."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:7
msgid "Either `splits` or `data_files` must be specified."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:9
msgid ""
"Name of the dataset processing script in PaddleNLP library or a custom "
"data reading function."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:12
msgid "Additional name to select a more specific dataset. Defaults to None."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:15
msgid ""
"Defining the path of dataset files. If None. `splits` must be specified. "
"Defaults to None."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:18
msgid ""
"Which split of the data to load. If None. `data_files` must be specified."
" Defaults to None."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:21
msgid ""
"Weather to return `MapDataset` or an `IterDataset`. True for "
"`IterDataset`. False for `MapDataset`. If None, return the default type "
"of this dataset. Defaults to None."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:25
msgid "Other keyword arguments to be passed to the `DatasetBuilder`."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:28
msgid "A `MapDataset` or `IterDataset` or a tuple of those."
msgstr ""

#: of paddlenlp.datasets.dataset.load_dataset:30
msgid ""
"For how to use this function, please see `dataset_load "
"<https://paddlenlp.readthedocs.io/zh/latest/data_prepare/dataset_load.html>`__"
" and `dataset_self_defined "
"<https://paddlenlp.readthedocs.io/zh/latest/data_prepare/dataset_self_defined.html>`__"
msgstr ""