Merge branch 'main' into dataset_infos-in-yaml

Author: lhoestq

README.md

@@ -25,8 +25,6 @@
     <a href="https://zenodo.org/badge/latestdoi/250213286"><img src="https://zenodo.org/badge/250213286.svg" alt="DOI"></a>
 </p>
 
-** ⚠️ The "master" branch has been renamed "main", please update your forks with [these instructions](https://github.com/huggingface/datasets/issues/4629)**
-
 🤗 Datasets is a lightweight library providing **two** main features:
 
 - **one-line dataloaders for many public datasets**: one-liners to download and pre-process any of the ![number of datasets](https://img.shields.io/endpoint?url=https://huggingface.co/api/shields/datasets&color=brightgreen) major public datasets (text datasets in 467 languages and dialects, image datasets, audio datasets, etc.) provided on the [HuggingFace Datasets Hub](https://huggingface.co/datasets). With a simple command like `squad_dataset = load_dataset("squad")`, get any of these datasets ready to use in a dataloader for training/evaluating a ML model (Numpy/Pandas/PyTorch/TensorFlow/JAX),

datasets/adv_glue/dataset_infos.json

@@ -1,6 +1,24 @@
 ---
-paperswithcode_id: compguesswhat
+annotations_creators:
+- machine-generated
+language:
+- en
+language_creators:
+- found
+license:
+- unknown
+multilinguality:
+- monolingual
 pretty_name: CompGuessWhat?!
+size_categories:
+- 100K<n<1M
+source_datasets:
+- extended|other-guesswhat
+task_categories:
+- visual-question-answering
+task_ids:
+- visual-question-answering
+paperswithcode_id: compguesswhat
 ---
 
 # Dataset Card for "compguesswhat"

datasets/compguesswhat/README.md

@@ -50,7 +50,7 @@ class Compguesswhat(datasets.GeneratorBasedBuilder):
             name="compguesswhat-original",
             gameplay_scenario="original",
             description="CompGuessWhat?! subset of games from the original GuessWhat?! dataset",
-            data_url="https://www.dropbox.com/s/l0nc13udml6vs0w/compguesswhat-original.zip?dl=1",
+            data_url="https://www.dropbox.com/s/qd9wlydpkpmq8rr/compguesswhat-original.zip?dl=1",
             splits={
                 "train": "compguesswhat.train.jsonl.gz",
                 "valid": "compguesswhat.valid.jsonl.gz",
@@ -61,7 +61,7 @@ class Compguesswhat(datasets.GeneratorBasedBuilder):
             name="compguesswhat-zero_shot",
             gameplay_scenario="zero_shot",
             description="CompGuessWhat?! reference set of games for zero-shot evaluation using NOCAPS images",
-            data_url="https://www.dropbox.com/s/gd46azul7o7iip4/compguesswhat-zero_shot.zip?dl=1",
+            data_url="https://www.dropbox.com/s/f5o2t7aiok7kpcm/compguesswhat-zero_shot.zip?dl=1",
             splits={
                 "nd_valid": "compguesswhat.nd_valid.jsonl.gz",
                 "nd_test": "compguesswhat.nd_test.jsonl.gz",

datasets/compguesswhat/compguesswhat.py

@@ -1 +1 @@
-{"compguesswhat-original": {"description": "\n        CompGuessWhat?! is an instance of a multi-task framework for evaluating the quality of learned neural representations,\n        in particular concerning attribute grounding. Use this dataset if you want to use the set of games whose reference\n        scene is an image in VisualGenome. Visit the website for more details: https://compguesswhat.github.io\n    ", "citation": "        @inproceedings{suglia2020compguesswhat,\n          title={CompGuessWhat?!: a Multi-task Evaluation Framework for Grounded Language Learning},\n          author={Suglia, Alessandro, Konstas, Ioannis, Vanzo, Andrea, Bastianelli, Emanuele, Desmond Elliott, Stella Frank and Oliver Lemon},\n          booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},\n          year={2020}\n        }\n    ", "homepage": "https://compguesswhat.github.io/", "license": "", "features": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "target_id": {"dtype": "int32", "id": null, "_type": "Value"}, "timestamp": {"dtype": "string", "id": null, "_type": "Value"}, "status": {"dtype": "string", "id": null, "_type": "Value"}, "image": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "file_name": {"dtype": "string", "id": null, "_type": "Value"}, "flickr_url": {"dtype": "string", "id": null, "_type": "Value"}, "coco_url": {"dtype": "string", "id": null, "_type": "Value"}, "height": {"dtype": "int32", "id": null, "_type": "Value"}, "width": {"dtype": "int32", "id": null, "_type": "Value"}, "visual_genome": {"width": {"dtype": "int32", "id": null, "_type": "Value"}, "height": {"dtype": "int32", "id": null, "_type": "Value"}, "url": {"dtype": "string", "id": null, "_type": "Value"}, "coco_id": {"dtype": "int32", "id": null, "_type": "Value"}, "flickr_id": {"dtype": "string", "id": null, "_type": "Value"}, "image_id": {"dtype": "string", "id": null, "_type": "Value"}}}, "qas": {"feature": {"question": {"dtype": "string", "id": null, "_type": "Value"}, "answer": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "int32", "id": null, "_type": "Value"}}, "length": -1, "id": null, "_type": "Sequence"}, "objects": {"feature": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "bbox": {"feature": {"dtype": "float32", "id": null, "_type": "Value"}, "length": 4, "id": null, "_type": "Sequence"}, "category": {"dtype": "string", "id": null, "_type": "Value"}, "area": {"dtype": "float32", "id": null, "_type": "Value"}, "category_id": {"dtype": "int32", "id": null, "_type": "Value"}, "segment": {"feature": {"feature": {"dtype": "float32", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "length": -1, "id": null, "_type": "Sequence"}}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "compguesswhat", "config_name": "compguesswhat-original", "version": {"version_str": "0.2.0", "description": "Second CompGuessWhat?! release", "major": 0, "minor": 2, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 123557020, "num_examples": 46341, "dataset_name": "compguesswhat"}, "validation": {"name": "validation", "num_bytes": 25441516, "num_examples": 9738, "dataset_name": "compguesswhat"}, "test": {"name": "test", "num_bytes": 25369315, "num_examples": 9621, "dataset_name": "compguesswhat"}}, "download_checksums": {"https://www.dropbox.com/s/l0nc13udml6vs0w/compguesswhat-original.zip?dl=1": {"num_bytes": 107201655, "checksum": "f965b469142cf65635b2b8b309ba2b28539fd7ad40039b11856cd662f2b000c1"}}, "download_size": 107201655, "post_processing_size": null, "dataset_size": 174367851, "size_in_bytes": 281569506}, "compguesswhat-zero_shot": {"description": "\n        CompGuessWhat?! is an instance of a multi-task framework for evaluating the quality of learned neural representations,\n        in particular concerning attribute grounding. Use this dataset if you want to use the set of games whose reference\n        scene is an image in VisualGenome. Visit the website for more details: https://compguesswhat.github.io\n    ", "citation": "        @inproceedings{suglia2020compguesswhat,\n          title={CompGuessWhat?!: a Multi-task Evaluation Framework for Grounded Language Learning},\n          author={Suglia, Alessandro, Konstas, Ioannis, Vanzo, Andrea, Bastianelli, Emanuele, Desmond Elliott, Stella Frank and Oliver Lemon},\n          booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},\n          year={2020}\n        }\n    ", "homepage": "https://compguesswhat.github.io/", "license": "", "features": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "target_id": {"dtype": "string", "id": null, "_type": "Value"}, "status": {"dtype": "string", "id": null, "_type": "Value"}, "image": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "file_name": {"dtype": "string", "id": null, "_type": "Value"}, "coco_url": {"dtype": "string", "id": null, "_type": "Value"}, "height": {"dtype": "int32", "id": null, "_type": "Value"}, "width": {"dtype": "int32", "id": null, "_type": "Value"}, "license": {"dtype": "int32", "id": null, "_type": "Value"}, "open_images_id": {"dtype": "string", "id": null, "_type": "Value"}, "date_captured": {"dtype": "string", "id": null, "_type": "Value"}}, "objects": {"feature": {"id": {"dtype": "string", "id": null, "_type": "Value"}, "bbox": {"feature": {"dtype": "float32", "id": null, "_type": "Value"}, "length": 4, "id": null, "_type": "Sequence"}, "category": {"dtype": "string", "id": null, "_type": "Value"}, "area": {"dtype": "float32", "id": null, "_type": "Value"}, "category_id": {"dtype": "int32", "id": null, "_type": "Value"}, "IsOccluded": {"dtype": "int32", "id": null, "_type": "Value"}, "IsTruncated": {"dtype": "int32", "id": null, "_type": "Value"}, "segment": {"feature": {"MaskPath": {"dtype": "string", "id": null, "_type": "Value"}, "LabelName": {"dtype": "string", "id": null, "_type": "Value"}, "BoxID": {"dtype": "string", "id": null, "_type": "Value"}, "BoxXMin": {"dtype": "string", "id": null, "_type": "Value"}, "BoxXMax": {"dtype": "string", "id": null, "_type": "Value"}, "BoxYMin": {"dtype": "string", "id": null, "_type": "Value"}, "BoxYMax": {"dtype": "string", "id": null, "_type": "Value"}, "PredictedIoU": {"dtype": "string", "id": null, "_type": "Value"}, "Clicks": {"dtype": "string", "id": null, "_type": "Value"}}, "length": -1, "id": null, "_type": "Sequence"}}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "compguesswhat", "config_name": "compguesswhat-zero_shot", "version": {"version_str": "0.2.0", "description": "Second CompGuessWhat?! release", "major": 0, "minor": 2, "patch": 0}, "splits": {"nd_valid": {"name": "nd_valid", "num_bytes": 13510725, "num_examples": 5343, "dataset_name": "compguesswhat"}, "nd_test": {"name": "nd_test", "num_bytes": 36228293, "num_examples": 13836, "dataset_name": "compguesswhat"}, "od_valid": {"name": "od_valid", "num_bytes": 14052108, "num_examples": 5372, "dataset_name": "compguesswhat"}, "od_test": {"name": "od_test", "num_bytes": 32951141, "num_examples": 13300, "dataset_name": "compguesswhat"}}, "download_checksums": {"https://www.dropbox.com/s/gd46azul7o7iip4/compguesswhat-zero_shot.zip?dl=1": {"num_bytes": 4845966, "checksum": "ebf444e14408dbff2d910ba9ec049cd42882f2ce52d465d0f78203ee454aa33e"}}, "download_size": 4845966, "post_processing_size": null, "dataset_size": 96742267, "size_in_bytes": 101588233}}
+{"compguesswhat-original": {"description": "\n        CompGuessWhat?! is an instance of a multi-task framework for evaluating the quality of learned neural representations,\n        in particular concerning attribute grounding. Use this dataset if you want to use the set of games whose reference\n        scene is an image in VisualGenome. Visit the website for more details: https://compguesswhat.github.io\n    ", "citation": "        @inproceedings{suglia2020compguesswhat,\n          title={CompGuessWhat?!: a Multi-task Evaluation Framework for Grounded Language Learning},\n          author={Suglia, Alessandro, Konstas, Ioannis, Vanzo, Andrea, Bastianelli, Emanuele, Desmond Elliott, Stella Frank and Oliver Lemon},\n          booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},\n          year={2020}\n        }\n    ", "homepage": "https://compguesswhat.github.io/", "license": "", "features": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "target_id": {"dtype": "int32", "id": null, "_type": "Value"}, "timestamp": {"dtype": "string", "id": null, "_type": "Value"}, "status": {"dtype": "string", "id": null, "_type": "Value"}, "image": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "file_name": {"dtype": "string", "id": null, "_type": "Value"}, "flickr_url": {"dtype": "string", "id": null, "_type": "Value"}, "coco_url": {"dtype": "string", "id": null, "_type": "Value"}, "height": {"dtype": "int32", "id": null, "_type": "Value"}, "width": {"dtype": "int32", "id": null, "_type": "Value"}, "visual_genome": {"width": {"dtype": "int32", "id": null, "_type": "Value"}, "height": {"dtype": "int32", "id": null, "_type": "Value"}, "url": {"dtype": "string", "id": null, "_type": "Value"}, "coco_id": {"dtype": "int32", "id": null, "_type": "Value"}, "flickr_id": {"dtype": "string", "id": null, "_type": "Value"}, "image_id": {"dtype": "string", "id": null, "_type": "Value"}}}, "qas": {"feature": {"question": {"dtype": "string", "id": null, "_type": "Value"}, "answer": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "int32", "id": null, "_type": "Value"}}, "length": -1, "id": null, "_type": "Sequence"}, "objects": {"feature": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "bbox": {"feature": {"dtype": "float32", "id": null, "_type": "Value"}, "length": 4, "id": null, "_type": "Sequence"}, "category": {"dtype": "string", "id": null, "_type": "Value"}, "area": {"dtype": "float32", "id": null, "_type": "Value"}, "category_id": {"dtype": "int32", "id": null, "_type": "Value"}, "segment": {"feature": {"feature": {"dtype": "float32", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "length": -1, "id": null, "_type": "Sequence"}}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "compguesswhat", "config_name": "compguesswhat-original", "version": {"version_str": "0.2.0", "description": "Second CompGuessWhat?! release", "major": 0, "minor": 2, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 126548689, "num_examples": 46341, "dataset_name": "compguesswhat"}, "validation": {"name": "validation", "num_bytes": 26055261, "num_examples": 9738, "dataset_name": "compguesswhat"}, "test": {"name": "test", "num_bytes": 25981593, "num_examples": 9621, "dataset_name": "compguesswhat"}}, "download_checksums": {"https://www.dropbox.com/s/qd9wlydpkpmq8rr/compguesswhat-original.zip?dl=1": {"num_bytes": 107201655, "checksum": "f965b469142cf65635b2b8b309ba2b28539fd7ad40039b11856cd662f2b000c1"}}, "download_size": 107201655, "post_processing_size": null, "dataset_size": 178585543, "size_in_bytes": 285787198}, "compguesswhat-zero_shot": {"description": "\n        CompGuessWhat?! is an instance of a multi-task framework for evaluating the quality of learned neural representations,\n        in particular concerning attribute grounding. Use this dataset if you want to use the set of games whose reference\n        scene is an image in VisualGenome. Visit the website for more details: https://compguesswhat.github.io\n    ", "citation": "        @inproceedings{suglia2020compguesswhat,\n          title={CompGuessWhat?!: a Multi-task Evaluation Framework for Grounded Language Learning},\n          author={Suglia, Alessandro, Konstas, Ioannis, Vanzo, Andrea, Bastianelli, Emanuele, Desmond Elliott, Stella Frank and Oliver Lemon},\n          booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},\n          year={2020}\n        }\n    ", "homepage": "https://compguesswhat.github.io/", "license": "", "features": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "target_id": {"dtype": "string", "id": null, "_type": "Value"}, "status": {"dtype": "string", "id": null, "_type": "Value"}, "image": {"id": {"dtype": "int32", "id": null, "_type": "Value"}, "file_name": {"dtype": "string", "id": null, "_type": "Value"}, "coco_url": {"dtype": "string", "id": null, "_type": "Value"}, "height": {"dtype": "int32", "id": null, "_type": "Value"}, "width": {"dtype": "int32", "id": null, "_type": "Value"}, "license": {"dtype": "int32", "id": null, "_type": "Value"}, "open_images_id": {"dtype": "string", "id": null, "_type": "Value"}, "date_captured": {"dtype": "string", "id": null, "_type": "Value"}}, "objects": {"feature": {"id": {"dtype": "string", "id": null, "_type": "Value"}, "bbox": {"feature": {"dtype": "float32", "id": null, "_type": "Value"}, "length": 4, "id": null, "_type": "Sequence"}, "category": {"dtype": "string", "id": null, "_type": "Value"}, "area": {"dtype": "float32", "id": null, "_type": "Value"}, "category_id": {"dtype": "int32", "id": null, "_type": "Value"}, "IsOccluded": {"dtype": "int32", "id": null, "_type": "Value"}, "IsTruncated": {"dtype": "int32", "id": null, "_type": "Value"}, "segment": {"feature": {"MaskPath": {"dtype": "string", "id": null, "_type": "Value"}, "LabelName": {"dtype": "string", "id": null, "_type": "Value"}, "BoxID": {"dtype": "string", "id": null, "_type": "Value"}, "BoxXMin": {"dtype": "string", "id": null, "_type": "Value"}, "BoxXMax": {"dtype": "string", "id": null, "_type": "Value"}, "BoxYMin": {"dtype": "string", "id": null, "_type": "Value"}, "BoxYMax": {"dtype": "string", "id": null, "_type": "Value"}, "PredictedIoU": {"dtype": "string", "id": null, "_type": "Value"}, "Clicks": {"dtype": "string", "id": null, "_type": "Value"}}, "length": -1, "id": null, "_type": "Sequence"}}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "compguesswhat", "config_name": "compguesswhat-zero_shot", "version": {"version_str": "0.2.0", "description": "Second CompGuessWhat?! release", "major": 0, "minor": 2, "patch": 0}, "splits": {"nd_valid": {"name": "nd_valid", "num_bytes": 13557059, "num_examples": 5343, "dataset_name": "compguesswhat"}, "nd_test": {"name": "nd_test", "num_bytes": 36352201, "num_examples": 13836, "dataset_name": "compguesswhat"}, "od_valid": {"name": "od_valid", "num_bytes": 14093233, "num_examples": 5372, "dataset_name": "compguesswhat"}, "od_test": {"name": "od_test", "num_bytes": 33049755, "num_examples": 13300, "dataset_name": "compguesswhat"}}, "download_checksums": {"https://www.dropbox.com/s/f5o2t7aiok7kpcm/compguesswhat-zero_shot.zip?dl=1": {"num_bytes": 4845966, "checksum": "ebf444e14408dbff2d910ba9ec049cd42882f2ce52d465d0f78203ee454aa33e"}}, "download_size": 4845966, "post_processing_size": null, "dataset_size": 97052248, "size_in_bytes": 101898214}}