| import csv | |
| import json | |
| import os | |
| import datasets | |
| import pandas as pd | |
| import numpy as np | |
| # TODO: Add BibTeX citation | |
| # Find for instance the citation on arxiv or on the dataset repo/website | |
| _CITATION = """\ | |
| @InProceedings{huggingface:dataset, | |
| title = {A great new dataset}, | |
| author={huggingface, Inc. | |
| }, | |
| year={2020} | |
| } | |
| """ | |
| # TODO: Add description of the dataset here | |
| # You can copy an official description | |
| _DESCRIPTION = """\ | |
| This new dataset is designed to solve this great NLP task and is crafted with a lot of care. | |
| """ | |
| # TODO: Add a link to an official homepage for the dataset here | |
| _HOMEPAGE = "" | |
| # TODO: Add the licence for the dataset here if you can find it | |
| _LICENSE = "" | |
| # TODO: Add link to the official dataset URLs here | |
| # The HuggingFace dataset library don't host the datasets but only point to the original files | |
| # This can be an arbitrary nested dict/list of URLs (see below in `_split_generators` method) | |
| _URLs = { | |
| } | |
| # TODO: Name of the dataset usually match the script name with CamelCase instead of snake_case | |
| class COCODataset(datasets.GeneratorBasedBuilder): | |
| """TODO: Short description of my dataset.""" | |
| VERSION = datasets.Version("1.1.0") | |
| DEFAULT_CONFIG_NAME = "en" | |
| def _info(self): | |
| # TODO: This method specifies the datasets.DatasetInfo object which contains informations and typings for the dataset | |
| features = datasets.Features( | |
| { | |
| "id": datasets.Value("int64"), | |
| "en": datasets.Value("string"), | |
| "fr": datasets.Value("string"), | |
| "image_id": datasets.Value("int64"), | |
| "image_file": datasets.Value("string") | |
| # These are the features of your dataset like images, labels ... | |
| } | |
| ) | |
| return datasets.DatasetInfo( | |
| # This is the description that will appear on the datasets page. | |
| description=_DESCRIPTION, | |
| # This defines the different columns of the dataset and their types | |
| features=features, # Here we define them above because they are different between the two configurations | |
| # If there's a common (input, target) tuple from the features, | |
| # specify them here. They'll be used if as_supervised=True in | |
| # builder.as_dataset. | |
| supervised_keys=None, | |
| # Homepage of the dataset for documentation | |
| homepage=_HOMEPAGE, | |
| # License for the dataset if available | |
| license=_LICENSE, | |
| # Citation for the dataset | |
| citation=_CITATION, | |
| ) | |
| def _split_generators(self, dl_manager): | |
| """Returns SplitGenerators.""" | |
| # TODO: This method is tasked with downloading/extracting the data and defining the splits depending on the configuration | |
| # If several configurations are possible (listed in BUILDER_CONFIGS), the configuration selected by the user is in self.config.name | |
| data_dir = self.config.data_dir | |
| return [ | |
| datasets.SplitGenerator( | |
| name=datasets.Split.TRAIN, | |
| # These kwargs will be passed to _generate_examples | |
| gen_kwargs={ | |
| "data_dir": data_dir, | |
| "split": "train", | |
| }, | |
| ), | |
| datasets.SplitGenerator( | |
| name=datasets.Split.TEST, | |
| # These kwargs will be passed to _generate_examples | |
| gen_kwargs={ | |
| "data_dir": data_dir, | |
| "split": "test" | |
| }, | |
| ), | |
| datasets.SplitGenerator( | |
| name=datasets.Split.VALIDATION, | |
| # These kwargs will be passed to _generate_examples | |
| gen_kwargs={ | |
| "data_dir": data_dir, | |
| "split": "val", | |
| }, | |
| ), | |
| ] | |
| def _generate_examples( | |
| self, data_dir, split # method parameters are unpacked from `gen_kwargs` as given in `_split_generators` | |
| ): | |
| """ Yields examples as (key, example) tuples. """ | |
| # This method handles input defined in _split_generators to yield (key, example) tuples from the dataset. | |
| # The `key` is here for legacy reason (tfds) and is not important in itself. | |
| # /home/33611/caption/ | |
| # train2014 | |
| if split == 'dev': | |
| split == 'val' | |
| with open(os.path.join(data_dir, f'{split}.json')) as fp: | |
| examples = json.load(fp) | |
| for id_, ex in enumerate(examples): | |
| image_id = ex["image_id"] | |
| fn = f'COCO_{split}2014_{str(image_id).zfill(12)}.jpg' | |
| image_file = os.path.join(data_dir, f'{split}2014', fn) | |
| yield id_, { | |
| "id": ex["id"], | |
| "en": ex["caption"], | |
| "fr": ex["fr"], | |
| "image_id": ex["image_id"], | |
| "image_file": image_file | |
| } | |