search

j-min / DSG

Davidsonian Scene Graph (DSG) for Text-to-Image Evaluation (ICLR 2024)
https://google.github.io/dsg
74 stars 5 forks source link

which means annotation_id? #4

Open mazhengyu8282 opened 3 months ago

mazhengyu8282 commented 3 months ago

thanks for your amazing work! about the annotations(tifa_v1.0_question_answers.json),I want to ask: 1.Did you annotate DSG　from coco2014 or 2017? "coco_val_id"?but I cannot find the according number in val_instance2017.json or train_instance2017.json 2.which number means coco anno_id? { "id": "coco_435097", "caption": "Some very big furry brown bears in a big grass field.", "question": "is this a grass field?", "choices": [ "yes", "no" ], "answer": "yes", "element_type": "location", "element": "grass field", "coco_val_id": "471450" },

mazhengyu8282 commented 3 months ago

Can you open DSG-1k dataset images?

j-min commented 2 months ago

Hi @mazhengyu8282, the tifa_v1.0_question_answers.json is the same file from TIFA GitHub - https://github.com/Yushi-Hu/tifa/blob/main/tifa_v1.0/tifa_v1.0_question_answers.json. @Yushi-Hu, do you have the answer to this question?

j-min commented 2 months ago

Regarding the 2nd question, Can you open DSG-1k dataset images?, the DSG-1k dataset only consists of text prompts; you need to generate images with your T2I model.