21002 lines
601 KiB
JSON
Executable File
21002 lines
601 KiB
JSON
Executable File
[
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "private",
|
|
"gt_answers": "PRIVATE",
|
|
"image_path": "./data/IIIT5K/test/1002_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PARKING",
|
|
"image_path": "./data/IIIT5K/test/1002_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALUTES",
|
|
"image_path": "./data/IIIT5K/test/1009_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOLCE",
|
|
"image_path": "./data/IIIT5K/test/100_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GABBANA",
|
|
"image_path": "./data/IIIT5K/test/100_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "royalty",
|
|
"gt_answers": "REGENCY",
|
|
"image_path": "./data/IIIT5K/test/100_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/1016_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bank",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/1016_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/1016_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "india",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/1016_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KINGFISHER",
|
|
"image_path": "./data/IIIT5K/test/1017_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLEAR",
|
|
"image_path": "./data/IIIT5K/test/101_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHANNEL",
|
|
"image_path": "./data/IIIT5K/test/101_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "universal",
|
|
"gt_answers": "UNIVERSAL",
|
|
"image_path": "./data/IIIT5K/test/101_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STUDIOS",
|
|
"image_path": "./data/IIIT5K/test/101_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hollywood",
|
|
"gt_answers": "HOLLYWOOD",
|
|
"image_path": "./data/IIIT5K/test/101_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/101_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOAN",
|
|
"image_path": "./data/IIIT5K/test/1021_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "that",
|
|
"gt_answers": "THAT",
|
|
"image_path": "./data/IIIT5K/test/1021_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/1021_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOANS",
|
|
"image_path": "./data/IIIT5K/test/1021_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JAMMU",
|
|
"image_path": "./data/IIIT5K/test/1023_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "41KM",
|
|
"image_path": "./data/IIIT5K/test/1023_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "83KM",
|
|
"image_path": "./data/IIIT5K/test/1023_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VISIT",
|
|
"image_path": "./data/IIIT5K/test/1023_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AGAIN",
|
|
"image_path": "./data/IIIT5K/test/1023_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/1023_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAPPY",
|
|
"image_path": "./data/IIIT5K/test/1023_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JOURNEY",
|
|
"image_path": "./data/IIIT5K/test/1023_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/1024_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/1024_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/1024_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/1024_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/1026_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VISA",
|
|
"image_path": "./data/IIIT5K/test/1026_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PLATINUM",
|
|
"image_path": "./data/IIIT5K/test/1026_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4865",
|
|
"image_path": "./data/IIIT5K/test/1026_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4567",
|
|
"image_path": "./data/IIIT5K/test/1026_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1212",
|
|
"image_path": "./data/IIIT5K/test/1026_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIJAY",
|
|
"image_path": "./data/IIIT5K/test/1026_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gypsy",
|
|
"gt_answers": "GYPSY",
|
|
"image_path": "./data/IIIT5K/test/102_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "05",
|
|
"image_path": "./data/IIIT5K/test/102_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/1036_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/1036_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/1036_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LABBIPET",
|
|
"image_path": "./data/IIIT5K/test/1036_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIJAYAWADA",
|
|
"image_path": "./data/IIIT5K/test/1036_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GRUHA",
|
|
"image_path": "./data/IIIT5K/test/1036_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GAMYA",
|
|
"image_path": "./data/IIIT5K/test/1036_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALDO",
|
|
"image_path": "./data/IIIT5K/test/103_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "royalty",
|
|
"gt_answers": "REGENCY",
|
|
"image_path": "./data/IIIT5K/test/103_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAND",
|
|
"image_path": "./data/IIIT5K/test/1041_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shark",
|
|
"gt_answers": "SHARK",
|
|
"image_path": "./data/IIIT5K/test/1041_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAGER",
|
|
"image_path": "./data/IIIT5K/test/1041_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "M",
|
|
"image_path": "./data/IIIT5K/test/1043_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAMMOTH",
|
|
"image_path": "./data/IIIT5K/test/1043_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/1044_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BLUBBER",
|
|
"image_path": "./data/IIIT5K/test/1044_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GO",
|
|
"image_path": "./data/IIIT5K/test/1044_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "no vegetarian",
|
|
"gt_answers": "VEGETARIAN",
|
|
"image_path": "./data/IIIT5K/test/1044_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/1045_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/1045_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/1046_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MUTUAL",
|
|
"image_path": "./data/IIIT5K/test/1046_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fund",
|
|
"gt_answers": "FUND",
|
|
"image_path": "./data/IIIT5K/test/1046_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/1047_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/1047_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/1047_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "india",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/1048_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/1049_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/1049_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWTOPSTOCKRESEARCHCOM",
|
|
"image_path": "./data/IIIT5K/test/1049_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWTOPSTOCKRESEARCHCOM",
|
|
"image_path": "./data/IIIT5K/test/1049_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DELOCATED",
|
|
"image_path": "./data/IIIT5K/test/104_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REGENCY",
|
|
"image_path": "./data/IIIT5K/test/104_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/1050_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BY",
|
|
"image_path": "./data/IIIT5K/test/1050_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWTOPSTOCKRESEARCHCOM",
|
|
"image_path": "./data/IIIT5K/test/1050_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWTOPSTOCKRESEARCHCOM",
|
|
"image_path": "./data/IIIT5K/test/1050_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHARTS",
|
|
"image_path": "./data/IIIT5K/test/1053_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BY",
|
|
"image_path": "./data/IIIT5K/test/1053_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWTOPSTOCKRESEARCHCOM",
|
|
"image_path": "./data/IIIT5K/test/1053_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FORMULA",
|
|
"image_path": "./data/IIIT5K/test/1055_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OBLOOM",
|
|
"image_path": "./data/IIIT5K/test/1056_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OBLOOM",
|
|
"image_path": "./data/IIIT5K/test/1056_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FREE",
|
|
"image_path": "./data/IIIT5K/test/1059_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PHONE",
|
|
"image_path": "./data/IIIT5K/test/1059_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "chicago",
|
|
"gt_answers": "CHICAGO",
|
|
"image_path": "./data/IIIT5K/test/1060_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "599",
|
|
"image_path": "./data/IIIT5K/test/1062_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "698",
|
|
"image_path": "./data/IIIT5K/test/1062_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "550",
|
|
"image_path": "./data/IIIT5K/test/1062_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1000",
|
|
"image_path": "./data/IIIT5K/test/1062_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "800",
|
|
"image_path": "./data/IIIT5K/test/1062_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "600",
|
|
"image_path": "./data/IIIT5K/test/1062_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/1063_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertising",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/1063_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "need",
|
|
"gt_answers": "NEED",
|
|
"image_path": "./data/IIIT5K/test/1063_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GET",
|
|
"image_path": "./data/IIIT5K/test/1063_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mcdonalds logo",
|
|
"gt_answers": "M",
|
|
"image_path": "./data/IIIT5K/test/1065_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "200",
|
|
"image_path": "./data/IIIT5K/test/1065_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "M",
|
|
"image_path": "./data/IIIT5K/test/1065_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "M",
|
|
"image_path": "./data/IIIT5K/test/1065_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "this",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/106_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/106_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "it",
|
|
"gt_answers": "IT",
|
|
"image_path": "./data/IIIT5K/test/106_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "yes",
|
|
"gt_answers": "YES",
|
|
"image_path": "./data/IIIT5K/test/106_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "no",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/106_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "royalty",
|
|
"gt_answers": "REGENCY",
|
|
"image_path": "./data/IIIT5K/test/106_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAC",
|
|
"image_path": "./data/IIIT5K/test/1072_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STORE",
|
|
"image_path": "./data/IIIT5K/test/1072_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WROUGHT",
|
|
"image_path": "./data/IIIT5K/test/1073_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGNBOARDS",
|
|
"image_path": "./data/IIIT5K/test/1073_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JOHNNY",
|
|
"image_path": "./data/IIIT5K/test/107_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEPP",
|
|
"image_path": "./data/IIIT5K/test/107_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/107_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "march",
|
|
"gt_answers": "MARCH",
|
|
"image_path": "./data/IIIT5K/test/107_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "station",
|
|
"gt_answers": "STATION",
|
|
"image_path": "./data/IIIT5K/test/1082_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STOP",
|
|
"image_path": "./data/IIIT5K/test/1082_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/108_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SERVICES",
|
|
"image_path": "./data/IIIT5K/test/108_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANKING",
|
|
"image_path": "./data/IIIT5K/test/108_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/108_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/108_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/108_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/108_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ABOUT",
|
|
"image_path": "./data/IIIT5K/test/108_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "US",
|
|
"image_path": "./data/IIIT5K/test/108_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRODUCTS",
|
|
"image_path": "./data/IIIT5K/test/108_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/1090_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JAZZ",
|
|
"image_path": "./data/IIIT5K/test/1092_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRO",
|
|
"image_path": "./data/IIIT5K/test/1094_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEXT",
|
|
"image_path": "./data/IIIT5K/test/1094_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXIT",
|
|
"image_path": "./data/IIIT5K/test/1094_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VENUS",
|
|
"image_path": "./data/IIIT5K/test/1095_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ITS",
|
|
"image_path": "./data/IIIT5K/test/1096_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/1096_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COLA",
|
|
"image_path": "./data/IIIT5K/test/1096_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUD",
|
|
"image_path": "./data/IIIT5K/test/1099_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "better",
|
|
"gt_answers": "BETTER",
|
|
"image_path": "./data/IIIT5K/test/1099_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TELL",
|
|
"image_path": "./data/IIIT5K/test/1099_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONTO",
|
|
"image_path": "./data/IIIT5K/test/1099_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BARTELT",
|
|
"image_path": "./data/IIIT5K/test/1099_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RD",
|
|
"image_path": "./data/IIIT5K/test/1099_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOBIES",
|
|
"image_path": "./data/IIIT5K/test/1099_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WOULDNT",
|
|
"image_path": "./data/IIIT5K/test/1099_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BE",
|
|
"image_path": "./data/IIIT5K/test/1099_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAUGHT",
|
|
"image_path": "./data/IIIT5K/test/1099_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PSP",
|
|
"image_path": "./data/IIIT5K/test/109_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IPAD",
|
|
"image_path": "./data/IIIT5K/test/10_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZOMBIES",
|
|
"image_path": "./data/IIIT5K/test/1102_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "attention",
|
|
"gt_answers": "ATTENTION",
|
|
"image_path": "./data/IIIT5K/test/1104_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WITH",
|
|
"image_path": "./data/IIIT5K/test/1104_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "billboard",
|
|
"gt_answers": "BILLBOARDS",
|
|
"image_path": "./data/IIIT5K/test/1104_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KOLESTON",
|
|
"image_path": "./data/IIIT5K/test/110_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JV",
|
|
"image_path": "./data/IIIT5K/test/112_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hotel",
|
|
"gt_answers": "HOTEL",
|
|
"image_path": "./data/IIIT5K/test/112_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLIMATE",
|
|
"image_path": "./data/IIIT5K/test/114_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ATMOSPHERE",
|
|
"image_path": "./data/IIIT5K/test/114_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AFFECTS",
|
|
"image_path": "./data/IIIT5K/test/114_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EVERYONE",
|
|
"image_path": "./data/IIIT5K/test/114_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3642039031055",
|
|
"image_path": "./data/IIIT5K/test/114_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "greenhouse",
|
|
"gt_answers": "GREENHOUSE",
|
|
"image_path": "./data/IIIT5K/test/114_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GASES",
|
|
"image_path": "./data/IIIT5K/test/114_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/114_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OUR",
|
|
"image_path": "./data/IIIT5K/test/114_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOILET",
|
|
"image_path": "./data/IIIT5K/test/115_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GO",
|
|
"image_path": "./data/IIIT5K/test/117_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREEN",
|
|
"image_path": "./data/IIIT5K/test/117_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "who",
|
|
"gt_answers": "WHO",
|
|
"image_path": "./data/IIIT5K/test/11_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/11_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "salt",
|
|
"gt_answers": "SALT",
|
|
"image_path": "./data/IIIT5K/test/11_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "july 2012",
|
|
"gt_answers": "JULY",
|
|
"image_path": "./data/IIIT5K/test/11_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "23",
|
|
"image_path": "./data/IIIT5K/test/11_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "18",
|
|
"gt_answers": "18",
|
|
"image_path": "./data/IIIT5K/test/121_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "19",
|
|
"image_path": "./data/IIIT5K/test/121_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "25",
|
|
"image_path": "./data/IIIT5K/test/121_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "26",
|
|
"image_path": "./data/IIIT5K/test/121_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4",
|
|
"image_path": "./data/IIIT5K/test/122_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "payloads",
|
|
"gt_answers": "PAYLOADS",
|
|
"image_path": "./data/IIIT5K/test/122_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OUT",
|
|
"image_path": "./data/IIIT5K/test/122_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5",
|
|
"image_path": "./data/IIIT5K/test/122_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "roaches",
|
|
"gt_answers": "ROACHES",
|
|
"image_path": "./data/IIIT5K/test/122_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RECOMMEND",
|
|
"image_path": "./data/IIIT5K/test/122_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THEIR",
|
|
"image_path": "./data/IIIT5K/test/122_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "friend",
|
|
"gt_answers": "FRIEND",
|
|
"image_path": "./data/IIIT5K/test/122_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AS",
|
|
"image_path": "./data/IIIT5K/test/122_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "live",
|
|
"gt_answers": "LIVE",
|
|
"image_path": "./data/IIIT5K/test/127_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "love",
|
|
"gt_answers": "LOVE",
|
|
"image_path": "./data/IIIT5K/test/127_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "laugh",
|
|
"gt_answers": "LAUGH",
|
|
"image_path": "./data/IIIT5K/test/127_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PITT",
|
|
"image_path": "./data/IIIT5K/test/129_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LET",
|
|
"image_path": "./data/IIIT5K/test/129_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/129_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "madness",
|
|
"gt_answers": "MADNESS",
|
|
"image_path": "./data/IIIT5K/test/129_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEGIN",
|
|
"image_path": "./data/IIIT5K/test/129_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/12_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/133_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/133_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/133_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "kafe",
|
|
"gt_answers": "KAFE",
|
|
"image_path": "./data/IIIT5K/test/134_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CARLSBERG",
|
|
"image_path": "./data/IIIT5K/test/134_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "baby",
|
|
"gt_answers": "BABY",
|
|
"image_path": "./data/IIIT5K/test/134_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "T",
|
|
"image_path": "./data/IIIT5K/test/134_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cafe",
|
|
"gt_answers": "CAFE",
|
|
"image_path": "./data/IIIT5K/test/134_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIX",
|
|
"image_path": "./data/IIIT5K/test/135_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PETERS",
|
|
"image_path": "./data/IIIT5K/test/135_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARE",
|
|
"image_path": "./data/IIIT5K/test/135_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "better",
|
|
"gt_answers": "BETTER",
|
|
"image_path": "./data/IIIT5K/test/135_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONE",
|
|
"image_path": "./data/IIIT5K/test/135_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/137_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VOTE",
|
|
"image_path": "./data/IIIT5K/test/137_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LA",
|
|
"image_path": "./data/IIIT5K/test/137_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TIMES",
|
|
"image_path": "./data/IIIT5K/test/137_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ENDORSES",
|
|
"image_path": "./data/IIIT5K/test/137_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CARMEN",
|
|
"image_path": "./data/IIIT5K/test/137_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/137_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MARCH",
|
|
"image_path": "./data/IIIT5K/test/137_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3RD",
|
|
"image_path": "./data/IIIT5K/test/137_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "next",
|
|
"gt_answers": "NEXT",
|
|
"image_path": "./data/IIIT5K/test/138_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/138_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "eagle",
|
|
"gt_answers": "EAGLE",
|
|
"image_path": "./data/IIIT5K/test/138_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "river",
|
|
"gt_answers": "RIVER",
|
|
"image_path": "./data/IIIT5K/test/138_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "chain",
|
|
"gt_answers": "CHAIN",
|
|
"image_path": "./data/IIIT5K/test/138_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/138_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "lakes",
|
|
"gt_answers": "LAKES",
|
|
"image_path": "./data/IIIT5K/test/138_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "8779453965",
|
|
"image_path": "./data/IIIT5K/test/138_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TIME",
|
|
"image_path": "./data/IIIT5K/test/138_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "visit",
|
|
"gt_answers": "VISIT",
|
|
"image_path": "./data/IIIT5K/test/138_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WILD",
|
|
"image_path": "./data/IIIT5K/test/138_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the eagle",
|
|
"gt_answers": "EAGLE",
|
|
"image_path": "./data/IIIT5K/test/138_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LODGE",
|
|
"image_path": "./data/IIIT5K/test/138_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EAGLE",
|
|
"image_path": "./data/IIIT5K/test/138_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/138_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALE",
|
|
"image_path": "./data/IIIT5K/test/139_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "now",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/13_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "itunes",
|
|
"gt_answers": "ITUNES",
|
|
"image_path": "./data/IIIT5K/test/13_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADVERTISE",
|
|
"image_path": "./data/IIIT5K/test/140_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "here",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/140_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "18008091469",
|
|
"image_path": "./data/IIIT5K/test/140_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FREEWAYBILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/140_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/140_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/142_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAR",
|
|
"image_path": "./data/IIIT5K/test/142_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOAN",
|
|
"image_path": "./data/IIIT5K/test/142_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "I",
|
|
"image_path": "./data/IIIT5K/test/144_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COULD",
|
|
"image_path": "./data/IIIT5K/test/144_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORKING",
|
|
"image_path": "./data/IIIT5K/test/144_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SO",
|
|
"image_path": "./data/IIIT5K/test/144_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MUCH",
|
|
"image_path": "./data/IIIT5K/test/144_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HARDER",
|
|
"image_path": "./data/IIIT5K/test/144_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GO",
|
|
"image_path": "./data/IIIT5K/test/144_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THERES",
|
|
"image_path": "./data/IIIT5K/test/148_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/148_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREAT",
|
|
"image_path": "./data/IIIT5K/test/148_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAMP",
|
|
"image_path": "./data/IIIT5K/test/148_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OUT",
|
|
"image_path": "./data/IIIT5K/test/148_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THERE",
|
|
"image_path": "./data/IIIT5K/test/148_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SUMMER",
|
|
"image_path": "./data/IIIT5K/test/148_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THERES",
|
|
"image_path": "./data/IIIT5K/test/149_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREAT",
|
|
"image_path": "./data/IIIT5K/test/149_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAMP",
|
|
"image_path": "./data/IIIT5K/test/149_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OUT",
|
|
"image_path": "./data/IIIT5K/test/149_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THERE",
|
|
"image_path": "./data/IIIT5K/test/149_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SUMMER",
|
|
"image_path": "./data/IIIT5K/test/149_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "joe's",
|
|
"gt_answers": "JOES",
|
|
"image_path": "./data/IIIT5K/test/14_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THINK",
|
|
"image_path": "./data/IIIT5K/test/151_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BIG",
|
|
"image_path": "./data/IIIT5K/test/151_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IMAX",
|
|
"image_path": "./data/IIIT5K/test/151_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SNIP",
|
|
"image_path": "./data/IIIT5K/test/151_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SNIP",
|
|
"image_path": "./data/IIIT5K/test/151_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIP",
|
|
"image_path": "./data/IIIT5K/test/151_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertising",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/153_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertising",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/154_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "monster",
|
|
"gt_answers": "MONSTER",
|
|
"image_path": "./data/IIIT5K/test/155_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BIKE",
|
|
"image_path": "./data/IIIT5K/test/155_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALE",
|
|
"image_path": "./data/IIIT5K/test/155_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOING",
|
|
"image_path": "./data/IIIT5K/test/155_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/155_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOTION",
|
|
"image_path": "./data/IIIT5K/test/158_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/158_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARDS",
|
|
"image_path": "./data/IIIT5K/test/158_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COCACOLA",
|
|
"image_path": "./data/IIIT5K/test/159_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "flavor is action",
|
|
"gt_answers": "FLAVOR",
|
|
"image_path": "./data/IIIT5K/test/161_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BLOOM",
|
|
"image_path": "./data/IIIT5K/test/161_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "giant",
|
|
"gt_answers": "GIANT",
|
|
"image_path": "./data/IIIT5K/test/162_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3SIDED",
|
|
"image_path": "./data/IIIT5K/test/162_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "joe",
|
|
"gt_answers": "JOE",
|
|
"image_path": "./data/IIIT5K/test/162_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "it is a question",
|
|
"gt_answers": "BROWN",
|
|
"image_path": "./data/IIIT5K/test/162_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/167_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/167_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/167_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALE",
|
|
"image_path": "./data/IIIT5K/test/169_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PURCHASE",
|
|
"image_path": "./data/IIIT5K/test/169_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/169_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/169_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/169_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/170_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bank",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/170_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/170_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "india",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/170_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WITH",
|
|
"image_path": "./data/IIIT5K/test/170_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/170_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/170_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAY",
|
|
"image_path": "./data/IIIT5K/test/170_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/171_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AD",
|
|
"image_path": "./data/IIIT5K/test/171_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "here",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/171_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RELIANCE",
|
|
"image_path": "./data/IIIT5K/test/172_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "vidya nagar",
|
|
"gt_answers": "VIDYANAGAR",
|
|
"image_path": "./data/IIIT5K/test/174_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5",
|
|
"image_path": "./data/IIIT5K/test/174_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAFE",
|
|
"image_path": "./data/IIIT5K/test/176_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/177_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/177_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/177_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/177_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "crnu",
|
|
"gt_answers": "CRNU",
|
|
"image_path": "./data/IIIT5K/test/178_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "goro",
|
|
"gt_answers": "GORU",
|
|
"image_path": "./data/IIIT5K/test/178_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "montenegro",
|
|
"gt_answers": "MONTENEGRO",
|
|
"image_path": "./data/IIIT5K/test/178_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SCREW",
|
|
"image_path": "./data/IIIT5K/test/179_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "you",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/179_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LA",
|
|
"image_path": "./data/IIIT5K/test/179_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MIDDLE",
|
|
"image_path": "./data/IIIT5K/test/17_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RD",
|
|
"image_path": "./data/IIIT5K/test/17_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PARK",
|
|
"image_path": "./data/IIIT5K/test/180_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SONY",
|
|
"image_path": "./data/IIIT5K/test/181_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/184_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CUSTOMER",
|
|
"image_path": "./data/IIIT5K/test/184_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/184_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CUSTOMER",
|
|
"image_path": "./data/IIIT5K/test/184_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEERS",
|
|
"image_path": "./data/IIIT5K/test/186_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/187_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "life",
|
|
"gt_answers": "LIFE",
|
|
"image_path": "./data/IIIT5K/test/187_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INSURANCE",
|
|
"image_path": "./data/IIIT5K/test/187_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WITH",
|
|
"image_path": "./data/IIIT5K/test/187_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "US",
|
|
"image_path": "./data/IIIT5K/test/187_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOURE",
|
|
"image_path": "./data/IIIT5K/test/187_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NAGOYA",
|
|
"image_path": "./data/IIIT5K/test/188_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shizuoka",
|
|
"gt_answers": "SHIZUOKA",
|
|
"image_path": "./data/IIIT5K/test/188_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOYOTA",
|
|
"image_path": "./data/IIIT5K/test/188_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THRIVE",
|
|
"image_path": "./data/IIIT5K/test/189_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JUMBO",
|
|
"image_path": "./data/IIIT5K/test/190_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "30",
|
|
"image_path": "./data/IIIT5K/test/192_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "1",
|
|
"gt_answers": "11",
|
|
"image_path": "./data/IIIT5K/test/193_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "``kmph''",
|
|
"gt_answers": "KMPH",
|
|
"image_path": "./data/IIIT5K/test/193_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "batac",
|
|
"gt_answers": "BATAC",
|
|
"image_path": "./data/IIIT5K/test/195_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "poli",
|
|
"gt_answers": "POBL",
|
|
"image_path": "./data/IIIT5K/test/195_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAOAG",
|
|
"image_path": "./data/IIIT5K/test/195_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CITY",
|
|
"image_path": "./data/IIIT5K/test/195_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/197_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/197_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/197_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/197_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JALAN",
|
|
"image_path": "./data/IIIT5K/test/19_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sehala",
|
|
"gt_answers": "SEHALA",
|
|
"image_path": "./data/IIIT5K/test/19_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COCACOLA",
|
|
"image_path": "./data/IIIT5K/test/1_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "srisri",
|
|
"gt_answers": "SRISHTI",
|
|
"image_path": "./data/IIIT5K/test/2002_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEVELOPERS",
|
|
"image_path": "./data/IIIT5K/test/2002_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pvt",
|
|
"gt_answers": "PVT",
|
|
"image_path": "./data/IIIT5K/test/2002_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "torquay",
|
|
"gt_answers": "TORQUAY",
|
|
"image_path": "./data/IIIT5K/test/2003_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MANOR",
|
|
"image_path": "./data/IIIT5K/test/2003_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "osmosis",
|
|
"gt_answers": "OSMOSIS",
|
|
"image_path": "./data/IIIT5K/test/2004_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PHOENIX",
|
|
"image_path": "./data/IIIT5K/test/2004_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "agencies",
|
|
"gt_answers": "AGENCIES",
|
|
"image_path": "./data/IIIT5K/test/2004_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NANCY",
|
|
"image_path": "./data/IIIT5K/test/2005_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STURGEON",
|
|
"image_path": "./data/IIIT5K/test/2005_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "needlewoman",
|
|
"gt_answers": "NEEDLEWOMAN",
|
|
"image_path": "./data/IIIT5K/test/2005_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "10",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/2006_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5",
|
|
"image_path": "./data/IIIT5K/test/2007_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VALLEY",
|
|
"image_path": "./data/IIIT5K/test/2008_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "keepers",
|
|
"gt_answers": "KEEPERS",
|
|
"image_path": "./data/IIIT5K/test/2009_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2009_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2010_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FLANDERS",
|
|
"image_path": "./data/IIIT5K/test/2011_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fields",
|
|
"gt_answers": "FIELDS",
|
|
"image_path": "./data/IIIT5K/test/2011_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VILLA",
|
|
"image_path": "./data/IIIT5K/test/2012_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOLLY",
|
|
"image_path": "./data/IIIT5K/test/2012_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "50",
|
|
"image_path": "./data/IIIT5K/test/2013_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1",
|
|
"image_path": "./data/IIIT5K/test/2013_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "42",
|
|
"image_path": "./data/IIIT5K/test/2013_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WE",
|
|
"image_path": "./data/IIIT5K/test/2015_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHANGED",
|
|
"image_path": "./data/IIIT5K/test/2015_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EVEREST",
|
|
"image_path": "./data/IIIT5K/test/2017_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LTD",
|
|
"image_path": "./data/IIIT5K/test/2017_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2017_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EVEREST",
|
|
"image_path": "./data/IIIT5K/test/2017_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORLD",
|
|
"image_path": "./data/IIIT5K/test/2017_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PVT",
|
|
"image_path": "./data/IIIT5K/test/2017_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEFORE",
|
|
"image_path": "./data/IIIT5K/test/2018_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AFTER",
|
|
"image_path": "./data/IIIT5K/test/2018_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2020_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PEA",
|
|
"image_path": "./data/IIIT5K/test/2020_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POD",
|
|
"image_path": "./data/IIIT5K/test/2020_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "21",
|
|
"image_path": "./data/IIIT5K/test/2020_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CATALDOS",
|
|
"image_path": "./data/IIIT5K/test/2021_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "villa",
|
|
"gt_answers": "VILLA",
|
|
"image_path": "./data/IIIT5K/test/2021_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEL",
|
|
"image_path": "./data/IIIT5K/test/2021_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "lagoon",
|
|
"gt_answers": "LAGO",
|
|
"image_path": "./data/IIIT5K/test/2021_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "13",
|
|
"image_path": "./data/IIIT5K/test/2023_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "123",
|
|
"image_path": "./data/IIIT5K/test/2024_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BROAD",
|
|
"image_path": "./data/IIIT5K/test/2025_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAVEN",
|
|
"image_path": "./data/IIIT5K/test/2025_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIEW",
|
|
"image_path": "./data/IIIT5K/test/2025_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wisteria",
|
|
"gt_answers": "WISTERIA",
|
|
"image_path": "./data/IIIT5K/test/2026_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2026_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "paradise",
|
|
"gt_answers": "PARADISO",
|
|
"image_path": "./data/IIIT5K/test/2027_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "77",
|
|
"image_path": "./data/IIIT5K/test/2028_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNIVERSAL",
|
|
"image_path": "./data/IIIT5K/test/2031_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMMITTED",
|
|
"image_path": "./data/IIIT5K/test/2031_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "positive",
|
|
"gt_answers": "POSITIVE",
|
|
"image_path": "./data/IIIT5K/test/2031_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SUNIL",
|
|
"image_path": "./data/IIIT5K/test/2033_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MINISTRY",
|
|
"image_path": "./data/IIIT5K/test/2033_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STEEL",
|
|
"image_path": "./data/IIIT5K/test/2033_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOVT",
|
|
"image_path": "./data/IIIT5K/test/2033_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2033_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAKING",
|
|
"image_path": "./data/IIIT5K/test/2034_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOMORROW",
|
|
"image_path": "./data/IIIT5K/test/2034_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRIGHTER",
|
|
"image_path": "./data/IIIT5K/test/2034_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "change",
|
|
"gt_answers": "CHANGE",
|
|
"image_path": "./data/IIIT5K/test/2036_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EVERYTHING",
|
|
"image_path": "./data/IIIT5K/test/2036_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SANJAY",
|
|
"image_path": "./data/IIIT5K/test/2041_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gupta",
|
|
"gt_answers": "GUPTA",
|
|
"image_path": "./data/IIIT5K/test/2041_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2042_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOG",
|
|
"image_path": "./data/IIIT5K/test/2042_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WE",
|
|
"image_path": "./data/IIIT5K/test/2044_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHANGED",
|
|
"image_path": "./data/IIIT5K/test/2044_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2045_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "croft",
|
|
"gt_answers": "CROFT",
|
|
"image_path": "./data/IIIT5K/test/2045_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "269",
|
|
"image_path": "./data/IIIT5K/test/2045_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "belstaff",
|
|
"gt_answers": "BELSTEAD",
|
|
"image_path": "./data/IIIT5K/test/2045_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "road",
|
|
"gt_answers": "ROAD",
|
|
"image_path": "./data/IIIT5K/test/2045_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "C",
|
|
"image_path": "./data/IIIT5K/test/2046_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "560",
|
|
"image_path": "./data/IIIT5K/test/2046_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "betty",
|
|
"gt_answers": "BETTY",
|
|
"image_path": "./data/IIIT5K/test/2046_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "villa",
|
|
"gt_answers": "VILLA",
|
|
"image_path": "./data/IIIT5K/test/2046_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHARLES",
|
|
"image_path": "./data/IIIT5K/test/2049_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOSHER",
|
|
"image_path": "./data/IIIT5K/test/2049_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOBA",
|
|
"image_path": "./data/IIIT5K/test/204_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARCHANA",
|
|
"image_path": "./data/IIIT5K/test/2051_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GUPTA",
|
|
"image_path": "./data/IIIT5K/test/2051_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "36",
|
|
"image_path": "./data/IIIT5K/test/2052_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ash",
|
|
"gt_answers": "ASHA",
|
|
"image_path": "./data/IIIT5K/test/2053_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GRINDER",
|
|
"image_path": "./data/IIIT5K/test/2053_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "enjoy",
|
|
"gt_answers": "ENJOY",
|
|
"image_path": "./data/IIIT5K/test/2055_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2055_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AT",
|
|
"image_path": "./data/IIIT5K/test/2055_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PANCHGANI",
|
|
"image_path": "./data/IIIT5K/test/2055_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "branch",
|
|
"gt_answers": "BRANCH",
|
|
"image_path": "./data/IIIT5K/test/2055_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAND",
|
|
"image_path": "./data/IIIT5K/test/2055_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/2055_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AT",
|
|
"image_path": "./data/IIIT5K/test/2055_23.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAHABALESHWAR",
|
|
"image_path": "./data/IIIT5K/test/2055_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "way",
|
|
"gt_answers": "WAY",
|
|
"image_path": "./data/IIIT5K/test/2055_29.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2055_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOLL",
|
|
"image_path": "./data/IIIT5K/test/2055_30.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FREE",
|
|
"image_path": "./data/IIIT5K/test/2055_31.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STRAWBERRY",
|
|
"image_path": "./data/IIIT5K/test/2055_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WITH",
|
|
"image_path": "./data/IIIT5K/test/2055_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PLASTIC",
|
|
"image_path": "./data/IIIT5K/test/2055_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CURRENCY",
|
|
"image_path": "./data/IIIT5K/test/2055_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2055_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/2055_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EARTHSELLERS",
|
|
"image_path": "./data/IIIT5K/test/2058_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPENING",
|
|
"image_path": "./data/IIIT5K/test/2059_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shorty",
|
|
"gt_answers": "SHORTLY",
|
|
"image_path": "./data/IIIT5K/test/2059_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "open shop",
|
|
"gt_answers": "OPENING",
|
|
"image_path": "./data/IIIT5K/test/2059_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shorty",
|
|
"gt_answers": "SHORTLY",
|
|
"image_path": "./data/IIIT5K/test/2059_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/205_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ISNT",
|
|
"image_path": "./data/IIIT5K/test/205_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/205_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ITS",
|
|
"image_path": "./data/IIIT5K/test/205_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/205_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "power",
|
|
"gt_answers": "POWER",
|
|
"image_path": "./data/IIIT5K/test/205_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "plant",
|
|
"gt_answers": "PLANT",
|
|
"image_path": "./data/IIIT5K/test/205_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "maple",
|
|
"gt_answers": "MAPLE",
|
|
"image_path": "./data/IIIT5K/test/2061_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2061_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JALI",
|
|
"image_path": "./data/IIIT5K/test/2063_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AX",
|
|
"image_path": "./data/IIIT5K/test/2063_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JISBAH",
|
|
"image_path": "./data/IIIT5K/test/2063_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "77",
|
|
"image_path": "./data/IIIT5K/test/2064_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is squirrels",
|
|
"gt_answers": "SQUIRRELS",
|
|
"image_path": "./data/IIIT5K/test/2068_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "oak",
|
|
"gt_answers": "OAK",
|
|
"image_path": "./data/IIIT5K/test/2068_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOLF",
|
|
"image_path": "./data/IIIT5K/test/2070_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "view",
|
|
"gt_answers": "VIEW",
|
|
"image_path": "./data/IIIT5K/test/2070_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HUNTERS",
|
|
"image_path": "./data/IIIT5K/test/2071_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOON",
|
|
"image_path": "./data/IIIT5K/test/2071_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HONEYBEE",
|
|
"image_path": "./data/IIIT5K/test/2072_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2072_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FARTHINGS",
|
|
"image_path": "./data/IIIT5K/test/2073_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LINDSAY",
|
|
"image_path": "./data/IIIT5K/test/2074_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hawks",
|
|
"gt_answers": "HAWKS",
|
|
"image_path": "./data/IIIT5K/test/2075_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POINT",
|
|
"image_path": "./data/IIIT5K/test/2075_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLINE",
|
|
"image_path": "./data/IIIT5K/test/2077_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2078_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CO",
|
|
"image_path": "./data/IIIT5K/test/2078_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ltd",
|
|
"gt_answers": "LTD",
|
|
"image_path": "./data/IIIT5K/test/2078_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "key",
|
|
"gt_answers": "KEY",
|
|
"image_path": "./data/IIIT5K/test/2078_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GET",
|
|
"image_path": "./data/IIIT5K/test/2078_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UIS",
|
|
"image_path": "./data/IIIT5K/test/2078_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSEHOLDERS",
|
|
"image_path": "./data/IIIT5K/test/2078_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/207_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANKING",
|
|
"image_path": "./data/IIIT5K/test/207_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nothing",
|
|
"gt_answers": "NOTHING",
|
|
"image_path": "./data/IIIT5K/test/207_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ELSE",
|
|
"image_path": "./data/IIIT5K/test/207_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/207_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/207_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WITH",
|
|
"image_path": "./data/IIIT5K/test/207_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/207_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/207_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/207_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAY",
|
|
"image_path": "./data/IIIT5K/test/207_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PATTYS",
|
|
"image_path": "./data/IIIT5K/test/2081_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ART",
|
|
"image_path": "./data/IIIT5K/test/2081_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "barn",
|
|
"gt_answers": "BARN",
|
|
"image_path": "./data/IIIT5K/test/2081_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "iron",
|
|
"gt_answers": "IRON",
|
|
"image_path": "./data/IIIT5K/test/2081_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gene",
|
|
"gt_answers": "GENE",
|
|
"image_path": "./data/IIIT5K/test/2084_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "R",
|
|
"image_path": "./data/IIIT5K/test/2084_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARNTSEN",
|
|
"image_path": "./data/IIIT5K/test/2084_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "birds",
|
|
"gt_answers": "BIRDS",
|
|
"image_path": "./data/IIIT5K/test/2084_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EYE",
|
|
"image_path": "./data/IIIT5K/test/2084_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAPLE",
|
|
"image_path": "./data/IIIT5K/test/2084_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LA",
|
|
"image_path": "./data/IIIT5K/test/2086_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RESIDENCIA",
|
|
"image_path": "./data/IIIT5K/test/2086_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LA",
|
|
"image_path": "./data/IIIT5K/test/2086_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RESIDENCIA",
|
|
"image_path": "./data/IIIT5K/test/2086_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "7",
|
|
"gt_answers": "7",
|
|
"image_path": "./data/IIIT5K/test/2087_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "99",
|
|
"image_path": "./data/IIIT5K/test/2087_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2",
|
|
"image_path": "./data/IIIT5K/test/2088_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "oscar",
|
|
"gt_answers": "OSCAR",
|
|
"image_path": "./data/IIIT5K/test/2089_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/208_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bank",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/208_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/208_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OSCAR",
|
|
"image_path": "./data/IIIT5K/test/2090_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATES",
|
|
"image_path": "./data/IIIT5K/test/2092_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2092_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "boy",
|
|
"gt_answers": "BOY",
|
|
"image_path": "./data/IIIT5K/test/2092_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "joseph",
|
|
"gt_answers": "JOSEPH",
|
|
"image_path": "./data/IIIT5K/test/2092_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WECKESSER",
|
|
"image_path": "./data/IIIT5K/test/2092_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "APRIL",
|
|
"image_path": "./data/IIIT5K/test/2092_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNITED",
|
|
"image_path": "./data/IIIT5K/test/2092_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DASTOURI",
|
|
"image_path": "./data/IIIT5K/test/2093_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "I",
|
|
"image_path": "./data/IIIT5K/test/2094_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEVER",
|
|
"image_path": "./data/IIIT5K/test/2094_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MANY",
|
|
"image_path": "./data/IIIT5K/test/2094_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "we are colours",
|
|
"gt_answers": "COLOURS",
|
|
"image_path": "./data/IIIT5K/test/2094_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HEATH",
|
|
"image_path": "./data/IIIT5K/test/2095_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LANDS",
|
|
"image_path": "./data/IIIT5K/test/2095_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "7",
|
|
"gt_answers": "7",
|
|
"image_path": "./data/IIIT5K/test/2096_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/2097_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/209_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/209_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/209_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/209_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WITH",
|
|
"image_path": "./data/IIIT5K/test/209_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/209_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/209_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAY",
|
|
"image_path": "./data/IIIT5K/test/209_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "6",
|
|
"image_path": "./data/IIIT5K/test/2100_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MY",
|
|
"image_path": "./data/IIIT5K/test/2101_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEST",
|
|
"image_path": "./data/IIIT5K/test/2101_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KINGAVON",
|
|
"image_path": "./data/IIIT5K/test/2103_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "507A",
|
|
"image_path": "./data/IIIT5K/test/2103_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "15",
|
|
"gt_answers": "15",
|
|
"image_path": "./data/IIIT5K/test/2104_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "123456",
|
|
"image_path": "./data/IIIT5K/test/2105_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "7890",
|
|
"image_path": "./data/IIIT5K/test/2105_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "7890",
|
|
"image_path": "./data/IIIT5K/test/2105_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "17335",
|
|
"image_path": "./data/IIIT5K/test/2106_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "16",
|
|
"gt_answers": "16",
|
|
"image_path": "./data/IIIT5K/test/2107_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tdk",
|
|
"gt_answers": "TDK",
|
|
"image_path": "./data/IIIT5K/test/2109_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SANYO",
|
|
"image_path": "./data/IIIT5K/test/2109_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "everyday",
|
|
"gt_answers": "EVERYDAY",
|
|
"image_path": "./data/IIIT5K/test/210_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FUNNY",
|
|
"image_path": "./data/IIIT5K/test/210_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FUNNY",
|
|
"image_path": "./data/IIIT5K/test/210_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "loading",
|
|
"gt_answers": "LOADING",
|
|
"image_path": "./data/IIIT5K/test/210_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STEP",
|
|
"image_path": "./data/IIIT5K/test/2110_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2112_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/2114_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CURRENTLY",
|
|
"image_path": "./data/IIIT5K/test/2114_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNAVAILABLE",
|
|
"image_path": "./data/IIIT5K/test/2114_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CURRENTLY",
|
|
"image_path": "./data/IIIT5K/test/2115_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNAVAILABLE",
|
|
"image_path": "./data/IIIT5K/test/2115_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FLICKER",
|
|
"image_path": "./data/IIIT5K/test/2115_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "50",
|
|
"gt_answers": "50",
|
|
"image_path": "./data/IIIT5K/test/2117_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nagashima",
|
|
"gt_answers": "NAGASHIMA",
|
|
"image_path": "./data/IIIT5K/test/2119_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "6",
|
|
"image_path": "./data/IIIT5K/test/2119_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "15",
|
|
"image_path": "./data/IIIT5K/test/2119_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is imazumi",
|
|
"gt_answers": "IMAIZUMI",
|
|
"image_path": "./data/IIIT5K/test/2119_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HEART",
|
|
"image_path": "./data/IIIT5K/test/2123_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/2124_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CARTER",
|
|
"image_path": "./data/IIIT5K/test/2124_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2124_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1949",
|
|
"image_path": "./data/IIIT5K/test/2124_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZAJAZD",
|
|
"image_path": "./data/IIIT5K/test/2126_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POD",
|
|
"image_path": "./data/IIIT5K/test/2126_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/2127_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CARTER",
|
|
"image_path": "./data/IIIT5K/test/2127_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2127_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1949",
|
|
"image_path": "./data/IIIT5K/test/2127_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FERNDALE",
|
|
"image_path": "./data/IIIT5K/test/2128_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LEE",
|
|
"image_path": "./data/IIIT5K/test/2128_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHORE",
|
|
"image_path": "./data/IIIT5K/test/2128_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PIPPITS",
|
|
"image_path": "./data/IIIT5K/test/2128_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2128_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2128_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "web",
|
|
"gt_answers": "WWWWEBSCOM",
|
|
"image_path": "./data/IIIT5K/test/2129_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IMAGE",
|
|
"image_path": "./data/IIIT5K/test/2129_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOT",
|
|
"image_path": "./data/IIIT5K/test/2129_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOUND",
|
|
"image_path": "./data/IIIT5K/test/2129_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hosting",
|
|
"gt_answers": "HOSTING",
|
|
"image_path": "./data/IIIT5K/test/2129_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3",
|
|
"image_path": "./data/IIIT5K/test/2131_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "215",
|
|
"image_path": "./data/IIIT5K/test/2132_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is 16",
|
|
"gt_answers": "16",
|
|
"image_path": "./data/IIIT5K/test/2133_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "8146",
|
|
"image_path": "./data/IIIT5K/test/2141_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHELSEA",
|
|
"image_path": "./data/IIIT5K/test/2144_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOOTBALL",
|
|
"image_path": "./data/IIIT5K/test/2144_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLUB",
|
|
"image_path": "./data/IIIT5K/test/2144_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "17D",
|
|
"image_path": "./data/IIIT5K/test/2148_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/2150_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/2151_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HARDWARE",
|
|
"image_path": "./data/IIIT5K/test/2153_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "30",
|
|
"image_path": "./data/IIIT5K/test/2155_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SANGHAVIE",
|
|
"image_path": "./data/IIIT5K/test/2156_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TRUSTPASS",
|
|
"image_path": "./data/IIIT5K/test/2156_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/2156_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIGHT",
|
|
"image_path": "./data/IIIT5K/test/2157_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3602",
|
|
"image_path": "./data/IIIT5K/test/2158_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3213",
|
|
"image_path": "./data/IIIT5K/test/2159_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GODIER",
|
|
"image_path": "./data/IIIT5K/test/2162_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "71",
|
|
"image_path": "./data/IIIT5K/test/2163_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "888",
|
|
"image_path": "./data/IIIT5K/test/2165_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NBNOVELTY",
|
|
"image_path": "./data/IIIT5K/test/2165_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "43",
|
|
"image_path": "./data/IIIT5K/test/2166_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "88",
|
|
"image_path": "./data/IIIT5K/test/2166_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "17",
|
|
"gt_answers": "17",
|
|
"image_path": "./data/IIIT5K/test/2166_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "220",
|
|
"image_path": "./data/IIIT5K/test/216_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PDG",
|
|
"image_path": "./data/IIIT5K/test/216_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tembak",
|
|
"gt_answers": "TEMBAK",
|
|
"image_path": "./data/IIIT5K/test/216_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "P",
|
|
"image_path": "./data/IIIT5K/test/216_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "221",
|
|
"image_path": "./data/IIIT5K/test/216_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "P",
|
|
"image_path": "./data/IIIT5K/test/216_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "221",
|
|
"image_path": "./data/IIIT5K/test/216_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hitman",
|
|
"gt_answers": "HITAM",
|
|
"image_path": "./data/IIIT5K/test/216_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "kg",
|
|
"gt_answers": "KG",
|
|
"image_path": "./data/IIIT5K/test/216_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "melayu",
|
|
"gt_answers": "MELAYU",
|
|
"image_path": "./data/IIIT5K/test/216_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jones",
|
|
"gt_answers": "JONES",
|
|
"image_path": "./data/IIIT5K/test/2170_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "college",
|
|
"gt_answers": "COLLEGE",
|
|
"image_path": "./data/IIIT5K/test/2170_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALI",
|
|
"image_path": "./data/IIIT5K/test/2171_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHIPPING",
|
|
"image_path": "./data/IIIT5K/test/2171_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BITU",
|
|
"image_path": "./data/IIIT5K/test/2171_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WHOLESALE",
|
|
"image_path": "./data/IIIT5K/test/2171_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "888",
|
|
"image_path": "./data/IIIT5K/test/2172_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REFINED",
|
|
"image_path": "./data/IIIT5K/test/2174_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOYABEAN",
|
|
"image_path": "./data/IIIT5K/test/2174_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OIL",
|
|
"image_path": "./data/IIIT5K/test/2174_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SWAD",
|
|
"image_path": "./data/IIIT5K/test/2174_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SEHAT",
|
|
"image_path": "./data/IIIT5K/test/2174_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "22A",
|
|
"image_path": "./data/IIIT5K/test/2176_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWSHUTTERSTOCKCOM",
|
|
"image_path": "./data/IIIT5K/test/2176_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "60602974",
|
|
"image_path": "./data/IIIT5K/test/2176_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWSHUTTERSTOCKCOM",
|
|
"image_path": "./data/IIIT5K/test/2181_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "25096996",
|
|
"image_path": "./data/IIIT5K/test/2181_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MILAGRO",
|
|
"image_path": "./data/IIIT5K/test/2185_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "23",
|
|
"image_path": "./data/IIIT5K/test/2189_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "meadows",
|
|
"gt_answers": "MEADOWS",
|
|
"image_path": "./data/IIIT5K/test/2189_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLOSE",
|
|
"image_path": "./data/IIIT5K/test/2189_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CRANK",
|
|
"image_path": "./data/IIIT5K/test/218_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UP",
|
|
"image_path": "./data/IIIT5K/test/218_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/218_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INNER",
|
|
"image_path": "./data/IIIT5K/test/218_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "contact",
|
|
"gt_answers": "CONTACT",
|
|
"image_path": "./data/IIIT5K/test/2191_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "national",
|
|
"gt_answers": "NATIONAL",
|
|
"image_path": "./data/IIIT5K/test/2192_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "1",
|
|
"gt_answers": "1",
|
|
"image_path": "./data/IIIT5K/test/2192_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "balance",
|
|
"gt_answers": "BALANCE",
|
|
"image_path": "./data/IIIT5K/test/2192_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2192_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TWENTY",
|
|
"image_path": "./data/IIIT5K/test/2196_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "65",
|
|
"image_path": "./data/IIIT5K/test/2196_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NW",
|
|
"image_path": "./data/IIIT5K/test/2196_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FLANDERS",
|
|
"image_path": "./data/IIIT5K/test/2196_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CRANK",
|
|
"image_path": "./data/IIIT5K/test/219_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UP",
|
|
"image_path": "./data/IIIT5K/test/219_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/219_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INNER",
|
|
"image_path": "./data/IIIT5K/test/219_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AC",
|
|
"image_path": "./data/IIIT5K/test/219_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/21_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "34",
|
|
"gt_answers": "34",
|
|
"image_path": "./data/IIIT5K/test/2200_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RECEPTION",
|
|
"image_path": "./data/IIIT5K/test/2200_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PARKING",
|
|
"image_path": "./data/IIIT5K/test/2200_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THREE",
|
|
"image_path": "./data/IIIT5K/test/2200_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MELROSE",
|
|
"image_path": "./data/IIIT5K/test/2200_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIX",
|
|
"image_path": "./data/IIIT5K/test/2200_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2200_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VALE",
|
|
"image_path": "./data/IIIT5K/test/2200_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GROSVENOR",
|
|
"image_path": "./data/IIIT5K/test/2200_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RESTAURANT",
|
|
"image_path": "./data/IIIT5K/test/2200_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "46",
|
|
"gt_answers": "46",
|
|
"image_path": "./data/IIIT5K/test/2201_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2201_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "31",
|
|
"image_path": "./data/IIIT5K/test/2201_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LGDNEY",
|
|
"image_path": "./data/IIIT5K/test/2201_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "167",
|
|
"image_path": "./data/IIIT5K/test/2201_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "40",
|
|
"gt_answers": "40",
|
|
"image_path": "./data/IIIT5K/test/2201_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "this",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/2202_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/2202_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "indoor",
|
|
"gt_answers": "INDOOR",
|
|
"image_path": "./data/IIIT5K/test/2202_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXCLUSIVE",
|
|
"image_path": "./data/IIIT5K/test/2204_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "development",
|
|
"gt_answers": "DEVELOPMENT",
|
|
"image_path": "./data/IIIT5K/test/2204_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OD",
|
|
"image_path": "./data/IIIT5K/test/2204_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1989",
|
|
"image_path": "./data/IIIT5K/test/2205_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BALL",
|
|
"image_path": "./data/IIIT5K/test/2205_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "contact",
|
|
"gt_answers": "CONTACT",
|
|
"image_path": "./data/IIIT5K/test/2206_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gloves",
|
|
"gt_answers": "GLOVES",
|
|
"image_path": "./data/IIIT5K/test/2209_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "49",
|
|
"image_path": "./data/IIIT5K/test/2209_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MICKEY",
|
|
"image_path": "./data/IIIT5K/test/220_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mickey's sweet",
|
|
"gt_answers": "SWEET",
|
|
"image_path": "./data/IIIT5K/test/220_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TEA",
|
|
"image_path": "./data/IIIT5K/test/220_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CORRESLAW",
|
|
"image_path": "./data/IIIT5K/test/2210_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOUTH",
|
|
"image_path": "./data/IIIT5K/test/2211_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOLME",
|
|
"image_path": "./data/IIIT5K/test/2211_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GLEN",
|
|
"image_path": "./data/IIIT5K/test/2211_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIDE",
|
|
"image_path": "./data/IIIT5K/test/2211_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/2220_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/2220_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gujarat",
|
|
"gt_answers": "GUJARAT",
|
|
"image_path": "./data/IIIT5K/test/2220_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AIRCEL",
|
|
"image_path": "./data/IIIT5K/test/2220_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "120",
|
|
"image_path": "./data/IIIT5K/test/2222_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STREET",
|
|
"image_path": "./data/IIIT5K/test/2223_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIGHT",
|
|
"image_path": "./data/IIIT5K/test/2223_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOLUTIONS",
|
|
"image_path": "./data/IIIT5K/test/2223_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAYS",
|
|
"image_path": "./data/IIIT5K/test/2225_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FREE",
|
|
"image_path": "./data/IIIT5K/test/2225_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "93",
|
|
"image_path": "./data/IIIT5K/test/2227_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "givenchy",
|
|
"gt_answers": "GIVENCHY",
|
|
"image_path": "./data/IIIT5K/test/222_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEWS",
|
|
"image_path": "./data/IIIT5K/test/2230_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "news made",
|
|
"gt_answers": "MADE",
|
|
"image_path": "./data/IIIT5K/test/2230_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXCITING",
|
|
"image_path": "./data/IIIT5K/test/2230_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEWS",
|
|
"image_path": "./data/IIIT5K/test/2231_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AP",
|
|
"image_path": "./data/IIIT5K/test/2232_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "QUAINTES",
|
|
"image_path": "./data/IIIT5K/test/2235_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2235_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "I",
|
|
"image_path": "./data/IIIT5K/test/2237_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DID",
|
|
"image_path": "./data/IIIT5K/test/2237_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/2237_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "I",
|
|
"image_path": "./data/IIIT5K/test/2237_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DO",
|
|
"image_path": "./data/IIIT5K/test/2237_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TEA",
|
|
"image_path": "./data/IIIT5K/test/223_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mickey mouse",
|
|
"gt_answers": "MICKEY",
|
|
"image_path": "./data/IIIT5K/test/223_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DS",
|
|
"image_path": "./data/IIIT5K/test/223_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CEYLINCO",
|
|
"image_path": "./data/IIIT5K/test/2240_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAY",
|
|
"image_path": "./data/IIIT5K/test/2244_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "dreamer",
|
|
"gt_answers": "DREAMER",
|
|
"image_path": "./data/IIIT5K/test/2244_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": ": jalan",
|
|
"gt_answers": "JALAN",
|
|
"image_path": "./data/IIIT5K/test/224_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "it is a sign",
|
|
"gt_answers": "MASJID",
|
|
"image_path": "./data/IIIT5K/test/224_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10200",
|
|
"image_path": "./data/IIIT5K/test/224_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is p pinang",
|
|
"gt_answers": "PPINANG",
|
|
"image_path": "./data/IIIT5K/test/224_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "lower",
|
|
"gt_answers": "LOWER",
|
|
"image_path": "./data/IIIT5K/test/2251_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mr combe",
|
|
"gt_answers": "COOMBE",
|
|
"image_path": "./data/IIIT5K/test/2251_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DIN",
|
|
"image_path": "./data/IIIT5K/test/2252_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JEETO",
|
|
"image_path": "./data/IIIT5K/test/2252_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VILLA",
|
|
"image_path": "./data/IIIT5K/test/2254_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "56",
|
|
"image_path": "./data/IIIT5K/test/2254_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3",
|
|
"image_path": "./data/IIIT5K/test/2254_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROSLYN",
|
|
"image_path": "./data/IIIT5K/test/2254_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AVE",
|
|
"image_path": "./data/IIIT5K/test/2254_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TAKOMA",
|
|
"image_path": "./data/IIIT5K/test/2254_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "154",
|
|
"image_path": "./data/IIIT5K/test/2254_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "172",
|
|
"image_path": "./data/IIIT5K/test/2255_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "64",
|
|
"image_path": "./data/IIIT5K/test/2255_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "39",
|
|
"gt_answers": "39",
|
|
"image_path": "./data/IIIT5K/test/2255_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "136",
|
|
"image_path": "./data/IIIT5K/test/2255_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INFO",
|
|
"image_path": "./data/IIIT5K/test/225_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAY",
|
|
"image_path": "./data/IIIT5K/test/225_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3RD",
|
|
"image_path": "./data/IIIT5K/test/225_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AUGUST",
|
|
"image_path": "./data/IIIT5K/test/225_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "11AM",
|
|
"image_path": "./data/IIIT5K/test/225_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "8PM",
|
|
"image_path": "./data/IIIT5K/test/225_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "motherwell ac",
|
|
"gt_answers": "WWWMOTHERWELLACUK",
|
|
"image_path": "./data/IIIT5K/test/225_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWPOSTERPLUSCOUK",
|
|
"image_path": "./data/IIIT5K/test/225_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2262_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLONES",
|
|
"image_path": "./data/IIIT5K/test/2262_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "15",
|
|
"gt_answers": "15",
|
|
"image_path": "./data/IIIT5K/test/2266_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/226_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/226_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/226_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ASSOCIATE",
|
|
"image_path": "./data/IIIT5K/test/226_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "banks",
|
|
"gt_answers": "BANKS",
|
|
"image_path": "./data/IIIT5K/test/226_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "8",
|
|
"image_path": "./data/IIIT5K/test/2273_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "45",
|
|
"gt_answers": "45",
|
|
"image_path": "./data/IIIT5K/test/2274_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ABBEY",
|
|
"image_path": "./data/IIIT5K/test/2276_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HILLCREST",
|
|
"image_path": "./data/IIIT5K/test/2279_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "63",
|
|
"image_path": "./data/IIIT5K/test/2281_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "15",
|
|
"gt_answers": "15",
|
|
"image_path": "./data/IIIT5K/test/2281_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "8",
|
|
"image_path": "./data/IIIT5K/test/2281_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HYGIENE",
|
|
"image_path": "./data/IIIT5K/test/2285_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "food",
|
|
"gt_answers": "FOOD",
|
|
"image_path": "./data/IIIT5K/test/2285_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "13",
|
|
"image_path": "./data/IIIT5K/test/2290_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CORRIE",
|
|
"image_path": "./data/IIIT5K/test/2290_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOLDINGS",
|
|
"image_path": "./data/IIIT5K/test/2290_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2291_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "malt",
|
|
"gt_answers": "MALT",
|
|
"image_path": "./data/IIIT5K/test/2291_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2291_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2571",
|
|
"image_path": "./data/IIIT5K/test/2294_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOUTH",
|
|
"image_path": "./data/IIIT5K/test/2294_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is pine",
|
|
"gt_answers": "PINE",
|
|
"image_path": "./data/IIIT5K/test/2294_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/2295_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NAMR",
|
|
"image_path": "./data/IIIT5K/test/2295_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "here",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/2295_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "oak",
|
|
"gt_answers": "OAK",
|
|
"image_path": "./data/IIIT5K/test/2297_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TREE",
|
|
"image_path": "./data/IIIT5K/test/2297_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "villas",
|
|
"gt_answers": "VILLAS",
|
|
"image_path": "./data/IIIT5K/test/2297_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "27",
|
|
"image_path": "./data/IIIT5K/test/2297_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "222",
|
|
"image_path": "./data/IIIT5K/test/2297_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OAK",
|
|
"image_path": "./data/IIIT5K/test/2298_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TREE",
|
|
"image_path": "./data/IIIT5K/test/2298_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "villas",
|
|
"gt_answers": "VILLAS",
|
|
"image_path": "./data/IIIT5K/test/2298_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "scho",
|
|
"gt_answers": "SCHO",
|
|
"image_path": "./data/IIIT5K/test/2299_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "field",
|
|
"gt_answers": "FIELD",
|
|
"image_path": "./data/IIIT5K/test/2299_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "road",
|
|
"gt_answers": "ROAD",
|
|
"image_path": "./data/IIIT5K/test/2299_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEDICSCIENTIST",
|
|
"image_path": "./data/IIIT5K/test/229_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NIKKI",
|
|
"image_path": "./data/IIIT5K/test/2301_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRADY",
|
|
"image_path": "./data/IIIT5K/test/2301_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KARI",
|
|
"image_path": "./data/IIIT5K/test/2301_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "view",
|
|
"gt_answers": "VIEW",
|
|
"image_path": "./data/IIIT5K/test/2303_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5",
|
|
"image_path": "./data/IIIT5K/test/2305_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertisement",
|
|
"gt_answers": "ADVERTISE",
|
|
"image_path": "./data/IIIT5K/test/230_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/230_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ME",
|
|
"image_path": "./data/IIIT5K/test/230_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ITS",
|
|
"image_path": "./data/IIIT5K/test/230_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EASIER",
|
|
"image_path": "./data/IIIT5K/test/230_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THAN",
|
|
"image_path": "./data/IIIT5K/test/230_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/230_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/2311_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "33",
|
|
"image_path": "./data/IIIT5K/test/2312_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "21",
|
|
"gt_answers": "21",
|
|
"image_path": "./data/IIIT5K/test/2313_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NUMBER",
|
|
"image_path": "./data/IIIT5K/test/2314_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SURREY",
|
|
"image_path": "./data/IIIT5K/test/2314_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEWS",
|
|
"image_path": "./data/IIIT5K/test/2314_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLICK",
|
|
"image_path": "./data/IIIT5K/test/2314_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "17",
|
|
"gt_answers": "17",
|
|
"image_path": "./data/IIIT5K/test/2316_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "penrose",
|
|
"gt_answers": "PENROSE",
|
|
"image_path": "./data/IIIT5K/test/2316_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COURT",
|
|
"image_path": "./data/IIIT5K/test/2316_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEALING",
|
|
"image_path": "./data/IIIT5K/test/2319_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "drugs",
|
|
"gt_answers": "DRUGS",
|
|
"image_path": "./data/IIIT5K/test/2319_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "don't",
|
|
"gt_answers": "DONT",
|
|
"image_path": "./data/IIIT5K/test/2319_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "well",
|
|
"gt_answers": "WELL",
|
|
"image_path": "./data/IIIT5K/test/2319_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ourselves",
|
|
"gt_answers": "OURSELVES",
|
|
"image_path": "./data/IIIT5K/test/2319_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/2319_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GIVE",
|
|
"image_path": "./data/IIIT5K/test/231_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAY",
|
|
"image_path": "./data/IIIT5K/test/231_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2419",
|
|
"image_path": "./data/IIIT5K/test/2320_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bellway",
|
|
"gt_answers": "BELLWAY",
|
|
"image_path": "./data/IIIT5K/test/2327_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STYLISH",
|
|
"image_path": "./data/IIIT5K/test/2327_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/2327_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAKING",
|
|
"image_path": "./data/IIIT5K/test/2329_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IT",
|
|
"image_path": "./data/IIIT5K/test/2329_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BETTER",
|
|
"image_path": "./data/IIIT5K/test/2329_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/232_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/232_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/232_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/232_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ivy",
|
|
"gt_answers": "IVY",
|
|
"image_path": "./data/IIIT5K/test/2332_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2332_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/2334_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "peace",
|
|
"gt_answers": "PEACE",
|
|
"image_path": "./data/IIIT5K/test/2335_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the name of the place",
|
|
"gt_answers": "HAVEN",
|
|
"image_path": "./data/IIIT5K/test/2335_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "child",
|
|
"gt_answers": "CHILD",
|
|
"image_path": "./data/IIIT5K/test/2336_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRST",
|
|
"image_path": "./data/IIIT5K/test/2336_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/2336_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "space",
|
|
"gt_answers": "SPACE",
|
|
"image_path": "./data/IIIT5K/test/2338_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/2338_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LESS",
|
|
"image_path": "./data/IIIT5K/test/2338_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CALA",
|
|
"image_path": "./data/IIIT5K/test/2340_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOMES",
|
|
"image_path": "./data/IIIT5K/test/2340_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AT",
|
|
"image_path": "./data/IIIT5K/test/2340_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/2342_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WELLCHILD",
|
|
"image_path": "./data/IIIT5K/test/2342_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VISITS",
|
|
"image_path": "./data/IIIT5K/test/2342_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/234_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/234_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/234_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KELLIMAR",
|
|
"image_path": "./data/IIIT5K/test/2351_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "89",
|
|
"image_path": "./data/IIIT5K/test/2352_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "maximus",
|
|
"gt_answers": "MAXIMUS",
|
|
"image_path": "./data/IIIT5K/test/2353_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "rio",
|
|
"gt_answers": "RIO",
|
|
"image_path": "./data/IIIT5K/test/2354_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5",
|
|
"image_path": "./data/IIIT5K/test/2357_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "10",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/2357_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "361",
|
|
"image_path": "./data/IIIT5K/test/2358_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "webs",
|
|
"gt_answers": "WEBS",
|
|
"image_path": "./data/IIIT5K/test/2359_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PROVIDES",
|
|
"image_path": "./data/IIIT5K/test/2359_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/2359_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOLF",
|
|
"image_path": "./data/IIIT5K/test/2361_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIEW",
|
|
"image_path": "./data/IIIT5K/test/2361_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2",
|
|
"image_path": "./data/IIIT5K/test/2361_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "22",
|
|
"image_path": "./data/IIIT5K/test/2361_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "100",
|
|
"image_path": "./data/IIIT5K/test/2362_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AWAYSIDE",
|
|
"image_path": "./data/IIIT5K/test/2365_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INNISKEEL",
|
|
"image_path": "./data/IIIT5K/test/2366_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AXHOLME",
|
|
"image_path": "./data/IIIT5K/test/2368_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "house",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2368_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "20721",
|
|
"image_path": "./data/IIIT5K/test/2370_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "miller",
|
|
"gt_answers": "MILLER",
|
|
"image_path": "./data/IIIT5K/test/2372_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "melin",
|
|
"gt_answers": "MELIN",
|
|
"image_path": "./data/IIIT5K/test/2374_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CWMLLWCHWR",
|
|
"image_path": "./data/IIIT5K/test/2374_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mill",
|
|
"gt_answers": "MILL",
|
|
"image_path": "./data/IIIT5K/test/2374_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GWALIAB",
|
|
"image_path": "./data/IIIT5K/test/2375_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "trade winds",
|
|
"gt_answers": "TRADEWINDS",
|
|
"image_path": "./data/IIIT5K/test/2380_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IMPERIAL",
|
|
"image_path": "./data/IIIT5K/test/2381_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mobile",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/2383_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PLAY",
|
|
"image_path": "./data/IIIT5K/test/2383_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/2383_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOTAL",
|
|
"image_path": "./data/IIIT5K/test/2385_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "what is written in the image",
|
|
"gt_answers": "HOARDINGS",
|
|
"image_path": "./data/IIIT5K/test/2385_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KELOWNA",
|
|
"image_path": "./data/IIIT5K/test/2386_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BMW",
|
|
"image_path": "./data/IIIT5K/test/2386_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4",
|
|
"image_path": "./data/IIIT5K/test/2387_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "1",
|
|
"gt_answers": "1",
|
|
"image_path": "./data/IIIT5K/test/238_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jalan",
|
|
"gt_answers": "JALAN",
|
|
"image_path": "./data/IIIT5K/test/238_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PENDIDIKAN",
|
|
"image_path": "./data/IIIT5K/test/238_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JINDALS",
|
|
"image_path": "./data/IIIT5K/test/2391_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "66",
|
|
"image_path": "./data/IIIT5K/test/2395_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cobble stone",
|
|
"gt_answers": "COBBLE",
|
|
"image_path": "./data/IIIT5K/test/2396_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4",
|
|
"image_path": "./data/IIIT5K/test/2398_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "7",
|
|
"image_path": "./data/IIIT5K/test/2399_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "9",
|
|
"image_path": "./data/IIIT5K/test/2400_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "high",
|
|
"gt_answers": "HIGH",
|
|
"image_path": "./data/IIIT5K/test/2402_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "trees",
|
|
"gt_answers": "TREES",
|
|
"image_path": "./data/IIIT5K/test/2402_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2403_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NAME",
|
|
"image_path": "./data/IIIT5K/test/2403_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/2403_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2404_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NAME",
|
|
"image_path": "./data/IIIT5K/test/2404_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2405_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "87",
|
|
"image_path": "./data/IIIT5K/test/2409_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "255",
|
|
"image_path": "./data/IIIT5K/test/2410_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "36",
|
|
"image_path": "./data/IIIT5K/test/2411_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jubilee",
|
|
"gt_answers": "JUBILEE",
|
|
"image_path": "./data/IIIT5K/test/2412_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RD",
|
|
"image_path": "./data/IIIT5K/test/2412_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "36",
|
|
"image_path": "./data/IIIT5K/test/2412_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "field",
|
|
"gt_answers": "FIELD",
|
|
"image_path": "./data/IIIT5K/test/2413_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREEN",
|
|
"image_path": "./data/IIIT5K/test/2413_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LODGE",
|
|
"image_path": "./data/IIIT5K/test/2413_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2415_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "kingsmead",
|
|
"gt_answers": "KINGSMEAD",
|
|
"image_path": "./data/IIIT5K/test/2415_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DINGLE",
|
|
"image_path": "./data/IIIT5K/test/2416_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RIKHYS",
|
|
"image_path": "./data/IIIT5K/test/2417_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ACCOUNTANCY",
|
|
"image_path": "./data/IIIT5K/test/2419_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/2419_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GLOBAL",
|
|
"image_path": "./data/IIIT5K/test/2419_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EN",
|
|
"image_path": "./data/IIIT5K/test/241_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/241_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/241_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ENJOY",
|
|
"image_path": "./data/IIIT5K/test/2421_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IT",
|
|
"image_path": "./data/IIIT5K/test/2421_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/2421_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "28",
|
|
"image_path": "./data/IIIT5K/test/2423_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAIER",
|
|
"image_path": "./data/IIIT5K/test/2424_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2424_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAIER",
|
|
"image_path": "./data/IIIT5K/test/2424_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "refrigerators",
|
|
"gt_answers": "REFRIGERATORS",
|
|
"image_path": "./data/IIIT5K/test/2424_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAIER",
|
|
"image_path": "./data/IIIT5K/test/2424_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "625",
|
|
"image_path": "./data/IIIT5K/test/2430_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KIRKSTONE",
|
|
"image_path": "./data/IIIT5K/test/2433_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CATHEDRAL",
|
|
"image_path": "./data/IIIT5K/test/2433_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ENTRANCE",
|
|
"image_path": "./data/IIIT5K/test/2433_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRATHAY",
|
|
"image_path": "./data/IIIT5K/test/2433_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SKELWITH",
|
|
"image_path": "./data/IIIT5K/test/2433_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INK",
|
|
"image_path": "./data/IIIT5K/test/2437_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CARTRIDGES",
|
|
"image_path": "./data/IIIT5K/test/2437_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWW",
|
|
"image_path": "./data/IIIT5K/test/243_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/243_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/243_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TWIN",
|
|
"image_path": "./data/IIIT5K/test/2444_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OAKS",
|
|
"image_path": "./data/IIIT5K/test/2444_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "54",
|
|
"image_path": "./data/IIIT5K/test/2444_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PROSPECT",
|
|
"image_path": "./data/IIIT5K/test/2447_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "street",
|
|
"gt_answers": "STREET",
|
|
"image_path": "./data/IIIT5K/test/2447_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2448_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "salmon",
|
|
"gt_answers": "SALMON",
|
|
"image_path": "./data/IIIT5K/test/2448_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWW",
|
|
"image_path": "./data/IIIT5K/test/244_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/244_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/244_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "brook",
|
|
"gt_answers": "BROOK",
|
|
"image_path": "./data/IIIT5K/test/2450_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "house",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2450_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "23",
|
|
"image_path": "./data/IIIT5K/test/2453_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VALERIE",
|
|
"image_path": "./data/IIIT5K/test/2457_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LACEY",
|
|
"image_path": "./data/IIIT5K/test/2458_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TC",
|
|
"image_path": "./data/IIIT5K/test/245_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ISTANBUL",
|
|
"image_path": "./data/IIIT5K/test/245_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "university",
|
|
"gt_answers": "UNIVERSITESI",
|
|
"image_path": "./data/IIIT5K/test/245_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AVCILAR",
|
|
"image_path": "./data/IIIT5K/test/245_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YERLESKESI",
|
|
"image_path": "./data/IIIT5K/test/245_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "101",
|
|
"image_path": "./data/IIIT5K/test/2461_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRICES",
|
|
"image_path": "./data/IIIT5K/test/2462_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OFF",
|
|
"image_path": "./data/IIIT5K/test/2462_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALE",
|
|
"image_path": "./data/IIIT5K/test/2462_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEWEST",
|
|
"image_path": "./data/IIIT5K/test/2463_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LUXURY",
|
|
"image_path": "./data/IIIT5K/test/2463_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADDRESS",
|
|
"image_path": "./data/IIIT5K/test/2463_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAPPY",
|
|
"image_path": "./data/IIIT5K/test/2464_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2464_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YEAR",
|
|
"image_path": "./data/IIIT5K/test/2464_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2469_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOOKOUT",
|
|
"image_path": "./data/IIIT5K/test/2469_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "58",
|
|
"image_path": "./data/IIIT5K/test/2470_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5",
|
|
"image_path": "./data/IIIT5K/test/2475_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RNAYE",
|
|
"image_path": "./data/IIIT5K/test/2477_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGNS",
|
|
"image_path": "./data/IIIT5K/test/2477_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "lake watere",
|
|
"gt_answers": "LAKETHWAITE",
|
|
"image_path": "./data/IIIT5K/test/2482_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2492_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "potting",
|
|
"gt_answers": "POTTING",
|
|
"image_path": "./data/IIIT5K/test/2492_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shed",
|
|
"gt_answers": "SHED",
|
|
"image_path": "./data/IIIT5K/test/2492_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2497_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "villa",
|
|
"gt_answers": "VILLA",
|
|
"image_path": "./data/IIIT5K/test/2497_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hill",
|
|
"gt_answers": "HILL",
|
|
"image_path": "./data/IIIT5K/test/2497_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "winsfield",
|
|
"gt_answers": "WINSFIELD",
|
|
"image_path": "./data/IIIT5K/test/2497_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEER",
|
|
"image_path": "./data/IIIT5K/test/249_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LED",
|
|
"image_path": "./data/IIIT5K/test/249_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEIJING",
|
|
"image_path": "./data/IIIT5K/test/24_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2008",
|
|
"image_path": "./data/IIIT5K/test/24_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GRANARY",
|
|
"image_path": "./data/IIIT5K/test/2502_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2502_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TWENTY",
|
|
"image_path": "./data/IIIT5K/test/2503_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EIGHT",
|
|
"image_path": "./data/IIIT5K/test/2503_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "54",
|
|
"image_path": "./data/IIIT5K/test/2504_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "22",
|
|
"image_path": "./data/IIIT5K/test/2508_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/2512_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/2512_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGN",
|
|
"image_path": "./data/IIIT5K/test/2512_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROLAND",
|
|
"image_path": "./data/IIIT5K/test/2512_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOWARD",
|
|
"image_path": "./data/IIIT5K/test/2512_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MD",
|
|
"image_path": "./data/IIIT5K/test/2512_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GRAHAMS",
|
|
"image_path": "./data/IIIT5K/test/2512_23.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GLENDALE",
|
|
"image_path": "./data/IIIT5K/test/2512_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MUM",
|
|
"image_path": "./data/IIIT5K/test/2512_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/2512_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAD",
|
|
"image_path": "./data/IIIT5K/test/2512_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROOM",
|
|
"image_path": "./data/IIIT5K/test/2512_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "23",
|
|
"image_path": "./data/IIIT5K/test/2515_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "38",
|
|
"image_path": "./data/IIIT5K/test/2516_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "22",
|
|
"image_path": "./data/IIIT5K/test/2517_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WISTERIA",
|
|
"image_path": "./data/IIIT5K/test/2520_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2520_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TWELVE",
|
|
"image_path": "./data/IIIT5K/test/2522_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DENE",
|
|
"image_path": "./data/IIIT5K/test/2522_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLOSE",
|
|
"image_path": "./data/IIIT5K/test/2522_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GULL",
|
|
"image_path": "./data/IIIT5K/test/2523_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/2523_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BURROW",
|
|
"image_path": "./data/IIIT5K/test/2523_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOURNESOL",
|
|
"image_path": "./data/IIIT5K/test/2523_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MILL",
|
|
"image_path": "./data/IIIT5K/test/2523_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2523_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOUR",
|
|
"image_path": "./data/IIIT5K/test/2523_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOLLY",
|
|
"image_path": "./data/IIIT5K/test/2523_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2523_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "badger",
|
|
"gt_answers": "BADGER",
|
|
"image_path": "./data/IIIT5K/test/2523_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2523_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2523_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "orchard",
|
|
"gt_answers": "ORCHARD",
|
|
"image_path": "./data/IIIT5K/test/2523_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2523_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "18",
|
|
"gt_answers": "18",
|
|
"image_path": "./data/IIIT5K/test/2523_23.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WISHING",
|
|
"image_path": "./data/IIIT5K/test/2523_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "well",
|
|
"gt_answers": "WELL",
|
|
"image_path": "./data/IIIT5K/test/2523_25.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "charlton",
|
|
"gt_answers": "CHARLTON",
|
|
"image_path": "./data/IIIT5K/test/2523_26.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "23",
|
|
"image_path": "./data/IIIT5K/test/2523_27.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GARDEN",
|
|
"image_path": "./data/IIIT5K/test/2523_28.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "kiswan",
|
|
"gt_answers": "KISWANI",
|
|
"image_path": "./data/IIIT5K/test/2523_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "harvest",
|
|
"gt_answers": "HARVEST",
|
|
"image_path": "./data/IIIT5K/test/2523_30.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "home",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/2523_31.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SUNGANAKA",
|
|
"image_path": "./data/IIIT5K/test/2523_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2523_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2523_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WELL",
|
|
"image_path": "./data/IIIT5K/test/2524_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIDE",
|
|
"image_path": "./data/IIIT5K/test/2524_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALDER",
|
|
"image_path": "./data/IIIT5K/test/2524_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLOSE",
|
|
"image_path": "./data/IIIT5K/test/2524_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PALMER",
|
|
"image_path": "./data/IIIT5K/test/2524_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLOSE",
|
|
"image_path": "./data/IIIT5K/test/2524_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wellfield",
|
|
"gt_answers": "WELLFIELD",
|
|
"image_path": "./data/IIIT5K/test/2524_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PLUM",
|
|
"image_path": "./data/IIIT5K/test/2524_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2524_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TREE",
|
|
"image_path": "./data/IIIT5K/test/2524_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2524_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ABBEY",
|
|
"image_path": "./data/IIIT5K/test/2524_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGES",
|
|
"image_path": "./data/IIIT5K/test/2524_23.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRTIT",
|
|
"image_path": "./data/IIIT5K/test/2524_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHRESTIAN",
|
|
"image_path": "./data/IIIT5K/test/2524_25.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ANDYS",
|
|
"image_path": "./data/IIIT5K/test/2524_26.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHED",
|
|
"image_path": "./data/IIIT5K/test/2524_27.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2524_28.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PIG",
|
|
"image_path": "./data/IIIT5K/test/2524_29.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROSE",
|
|
"image_path": "./data/IIIT5K/test/2524_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHED",
|
|
"image_path": "./data/IIIT5K/test/2524_30.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "studio",
|
|
"gt_answers": "STUDIO",
|
|
"image_path": "./data/IIIT5K/test/2524_31.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THISTLE",
|
|
"image_path": "./data/IIIT5K/test/2524_32.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GRANGE",
|
|
"image_path": "./data/IIIT5K/test/2524_33.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOURTEEN",
|
|
"image_path": "./data/IIIT5K/test/2524_34.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CROFT",
|
|
"image_path": "./data/IIIT5K/test/2524_35.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PLACE",
|
|
"image_path": "./data/IIIT5K/test/2524_36.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "12",
|
|
"image_path": "./data/IIIT5K/test/2524_37.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ELGIN",
|
|
"image_path": "./data/IIIT5K/test/2524_38.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DRIVE",
|
|
"image_path": "./data/IIIT5K/test/2524_39.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARBOUR",
|
|
"image_path": "./data/IIIT5K/test/2524_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ORCHARD",
|
|
"image_path": "./data/IIIT5K/test/2524_40.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2524_41.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TIGH",
|
|
"image_path": "./data/IIIT5K/test/2524_42.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AN",
|
|
"image_path": "./data/IIIT5K/test/2524_43.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EILEAN",
|
|
"image_path": "./data/IIIT5K/test/2524_44.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fuller",
|
|
"gt_answers": "FULLER",
|
|
"image_path": "./data/IIIT5K/test/2524_45.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2524_46.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NURSERY",
|
|
"image_path": "./data/IIIT5K/test/2524_47.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "badger",
|
|
"gt_answers": "BADGER",
|
|
"image_path": "./data/IIIT5K/test/2524_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2524_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shoe string",
|
|
"gt_answers": "SHOESTRING",
|
|
"image_path": "./data/IIIT5K/test/2524_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2524_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "stream",
|
|
"gt_answers": "STREAM",
|
|
"image_path": "./data/IIIT5K/test/2524_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "44",
|
|
"gt_answers": "44",
|
|
"image_path": "./data/IIIT5K/test/2525_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "280",
|
|
"image_path": "./data/IIIT5K/test/2526_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COUNTRY",
|
|
"image_path": "./data/IIIT5K/test/2527_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2528_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BLOOMERS",
|
|
"image_path": "./data/IIIT5K/test/2529_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "farm",
|
|
"gt_answers": "FARM",
|
|
"image_path": "./data/IIIT5K/test/2529_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hall",
|
|
"gt_answers": "HALL",
|
|
"image_path": "./data/IIIT5K/test/2529_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SONS",
|
|
"image_path": "./data/IIIT5K/test/2529_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHILD",
|
|
"image_path": "./data/IIIT5K/test/252_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/252_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOARD",
|
|
"image_path": "./data/IIIT5K/test/252_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MENLEN",
|
|
"image_path": "./data/IIIT5K/test/2530_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DLONRA",
|
|
"image_path": "./data/IIIT5K/test/2530_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GRANDADS",
|
|
"image_path": "./data/IIIT5K/test/2530_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEN",
|
|
"image_path": "./data/IIIT5K/test/2530_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2530_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WARREN",
|
|
"image_path": "./data/IIIT5K/test/2530_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GRANADO",
|
|
"image_path": "./data/IIIT5K/test/2530_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COLOSSEUM",
|
|
"image_path": "./data/IIIT5K/test/2533_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CO",
|
|
"image_path": "./data/IIIT5K/test/2533_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "uk",
|
|
"gt_answers": "UK",
|
|
"image_path": "./data/IIIT5K/test/2533_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VALIANT",
|
|
"image_path": "./data/IIIT5K/test/2535_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PARK",
|
|
"image_path": "./data/IIIT5K/test/2536_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "alexandra",
|
|
"gt_answers": "ALEXANDRA",
|
|
"image_path": "./data/IIIT5K/test/2536_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LETTING",
|
|
"image_path": "./data/IIIT5K/test/2536_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the two",
|
|
"gt_answers": "TWO",
|
|
"image_path": "./data/IIIT5K/test/2536_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sator",
|
|
"gt_answers": "SATOR",
|
|
"image_path": "./data/IIIT5K/test/2538_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AREPO",
|
|
"image_path": "./data/IIIT5K/test/2538_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TENET",
|
|
"image_path": "./data/IIIT5K/test/2538_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "opera",
|
|
"gt_answers": "OPERA",
|
|
"image_path": "./data/IIIT5K/test/2538_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "rotas",
|
|
"gt_answers": "ROTAS",
|
|
"image_path": "./data/IIIT5K/test/2538_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FLOWER",
|
|
"image_path": "./data/IIIT5K/test/2539_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HUA",
|
|
"image_path": "./data/IIIT5K/test/253_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHENG",
|
|
"image_path": "./data/IIIT5K/test/253_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "234",
|
|
"image_path": "./data/IIIT5K/test/2540_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "49",
|
|
"image_path": "./data/IIIT5K/test/2540_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4",
|
|
"image_path": "./data/IIIT5K/test/2540_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "34",
|
|
"gt_answers": "34",
|
|
"image_path": "./data/IIIT5K/test/2540_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4",
|
|
"image_path": "./data/IIIT5K/test/2540_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "8",
|
|
"image_path": "./data/IIIT5K/test/2540_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "234",
|
|
"image_path": "./data/IIIT5K/test/2540_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "slate",
|
|
"gt_answers": "SLATE",
|
|
"image_path": "./data/IIIT5K/test/2541_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAGNOLIA",
|
|
"image_path": "./data/IIIT5K/test/2541_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARTWORK",
|
|
"image_path": "./data/IIIT5K/test/2541_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OLD",
|
|
"image_path": "./data/IIIT5K/test/2541_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "english",
|
|
"gt_answers": "ENGLISH",
|
|
"image_path": "./data/IIIT5K/test/2541_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/2541_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "script",
|
|
"gt_answers": "SCRIPT",
|
|
"image_path": "./data/IIIT5K/test/2541_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "villa",
|
|
"gt_answers": "VILLA",
|
|
"image_path": "./data/IIIT5K/test/2543_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "54",
|
|
"image_path": "./data/IIIT5K/test/2544_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "three",
|
|
"gt_answers": "THREE",
|
|
"image_path": "./data/IIIT5K/test/2545_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "louise",
|
|
"gt_answers": "LOUISE",
|
|
"image_path": "./data/IIIT5K/test/2551_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "23",
|
|
"image_path": "./data/IIIT5K/test/2552_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "8",
|
|
"image_path": "./data/IIIT5K/test/2553_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRINTED",
|
|
"image_path": "./data/IIIT5K/test/2557_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOARDINGS",
|
|
"image_path": "./data/IIIT5K/test/2557_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FULL",
|
|
"image_path": "./data/IIIT5K/test/2557_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EN",
|
|
"image_path": "./data/IIIT5K/test/255_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/255_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nescafe",
|
|
"gt_answers": "NESCAFE",
|
|
"image_path": "./data/IIIT5K/test/2563_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tdk",
|
|
"gt_answers": "TDK",
|
|
"image_path": "./data/IIIT5K/test/2563_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SANYO",
|
|
"image_path": "./data/IIIT5K/test/2563_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nescafe",
|
|
"gt_answers": "NESCAFE",
|
|
"image_path": "./data/IIIT5K/test/2564_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TDK",
|
|
"image_path": "./data/IIIT5K/test/2564_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAMBETH",
|
|
"image_path": "./data/IIIT5K/test/2567_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EARLS",
|
|
"image_path": "./data/IIIT5K/test/2568_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "court",
|
|
"gt_answers": "COURT",
|
|
"image_path": "./data/IIIT5K/test/2568_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DESIGN",
|
|
"image_path": "./data/IIIT5K/test/2572_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COLLEGE",
|
|
"image_path": "./data/IIIT5K/test/2573_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DESHMUKH",
|
|
"image_path": "./data/IIIT5K/test/2576_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "atlantic",
|
|
"gt_answers": "ATLANTIC",
|
|
"image_path": "./data/IIIT5K/test/2577_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAFE",
|
|
"image_path": "./data/IIIT5K/test/2578_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/2578_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "city",
|
|
"gt_answers": "CITY",
|
|
"image_path": "./data/IIIT5K/test/2578_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "behold",
|
|
"gt_answers": "BEHOLD",
|
|
"image_path": "./data/IIIT5K/test/2579_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wonders",
|
|
"gt_answers": "WONDERS",
|
|
"image_path": "./data/IIIT5K/test/2579_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LARGE",
|
|
"image_path": "./data/IIIT5K/test/257_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LARGE",
|
|
"image_path": "./data/IIIT5K/test/257_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PIZZA",
|
|
"image_path": "./data/IIIT5K/test/257_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LARGE",
|
|
"image_path": "./data/IIIT5K/test/257_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "riverside",
|
|
"gt_answers": "RIVERSIDE",
|
|
"image_path": "./data/IIIT5K/test/2583_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HERITAGE",
|
|
"image_path": "./data/IIIT5K/test/2586_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALE",
|
|
"image_path": "./data/IIIT5K/test/2587_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOAD",
|
|
"image_path": "./data/IIIT5K/test/2588_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HALL",
|
|
"image_path": "./data/IIIT5K/test/2588_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SQUIRRELS",
|
|
"image_path": "./data/IIIT5K/test/2590_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROSE",
|
|
"image_path": "./data/IIIT5K/test/2591_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2591_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "5",
|
|
"gt_answers": "5",
|
|
"image_path": "./data/IIIT5K/test/2591_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "14",
|
|
"image_path": "./data/IIIT5K/test/2594_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "kings",
|
|
"gt_answers": "KINGS",
|
|
"image_path": "./data/IIIT5K/test/2594_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "rd",
|
|
"gt_answers": "RD",
|
|
"image_path": "./data/IIIT5K/test/2594_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fairview",
|
|
"gt_answers": "FAIRVIEW",
|
|
"image_path": "./data/IIIT5K/test/2596_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ST",
|
|
"image_path": "./data/IIIT5K/test/2596_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GUILDFORD",
|
|
"image_path": "./data/IIIT5K/test/2596_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "barn",
|
|
"gt_answers": "BARN",
|
|
"image_path": "./data/IIIT5K/test/2597_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "end",
|
|
"gt_answers": "END",
|
|
"image_path": "./data/IIIT5K/test/2597_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STAIRS",
|
|
"image_path": "./data/IIIT5K/test/2597_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OAST",
|
|
"image_path": "./data/IIIT5K/test/2597_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/2597_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "stairs",
|
|
"gt_answers": "STAIRS",
|
|
"image_path": "./data/IIIT5K/test/2597_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2598_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "APARTMENTS",
|
|
"image_path": "./data/IIIT5K/test/2599_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "020",
|
|
"image_path": "./data/IIIT5K/test/2599_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOGG",
|
|
"image_path": "./data/IIIT5K/test/2600_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "golf",
|
|
"gt_answers": "GOLF",
|
|
"image_path": "./data/IIIT5K/test/2603_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "health",
|
|
"gt_answers": "HEALTH",
|
|
"image_path": "./data/IIIT5K/test/2603_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MACHYNYS",
|
|
"image_path": "./data/IIIT5K/test/2603_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PENINSULA",
|
|
"image_path": "./data/IIIT5K/test/2603_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LET",
|
|
"image_path": "./data/IIIT5K/test/2609_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOWN",
|
|
"image_path": "./data/IIIT5K/test/2609_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BY",
|
|
"image_path": "./data/IIIT5K/test/2609_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRITIAN",
|
|
"image_path": "./data/IIIT5K/test/2609_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRST",
|
|
"image_path": "./data/IIIT5K/test/2609_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAUGHT",
|
|
"image_path": "./data/IIIT5K/test/260_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "get you",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/260_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOOKING",
|
|
"image_path": "./data/IIIT5K/test/260_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2611_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "19TH",
|
|
"image_path": "./data/IIIT5K/test/2611_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ITS",
|
|
"image_path": "./data/IIIT5K/test/2611_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "every",
|
|
"gt_answers": "EVERY",
|
|
"image_path": "./data/IIIT5K/test/2611_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tuli",
|
|
"gt_answers": "TULIN",
|
|
"image_path": "./data/IIIT5K/test/2611_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PREVENTION",
|
|
"image_path": "./data/IIIT5K/test/2611_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/2611_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHILD",
|
|
"image_path": "./data/IIIT5K/test/2611_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "daga's",
|
|
"gt_answers": "DAGAS",
|
|
"image_path": "./data/IIIT5K/test/2612_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RITRIK",
|
|
"image_path": "./data/IIIT5K/test/2612_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHALINI",
|
|
"image_path": "./data/IIIT5K/test/2612_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RAHUL",
|
|
"image_path": "./data/IIIT5K/test/2612_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THAKAAR",
|
|
"image_path": "./data/IIIT5K/test/2613_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SETH",
|
|
"image_path": "./data/IIIT5K/test/2613_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "75",
|
|
"image_path": "./data/IIIT5K/test/2615_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "alexander",
|
|
"gt_answers": "ALEXANDER",
|
|
"image_path": "./data/IIIT5K/test/2617_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "10",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/2617_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cottage",
|
|
"gt_answers": "COTTAGES",
|
|
"image_path": "./data/IIIT5K/test/2617_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cheshire",
|
|
"gt_answers": "CHESHIRE",
|
|
"image_path": "./data/IIIT5K/test/2618_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "view",
|
|
"gt_answers": "VIEW",
|
|
"image_path": "./data/IIIT5K/test/2618_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hunters",
|
|
"gt_answers": "HUNTERS",
|
|
"image_path": "./data/IIIT5K/test/2619_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "lodge",
|
|
"gt_answers": "LODGE",
|
|
"image_path": "./data/IIIT5K/test/2619_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "P",
|
|
"image_path": "./data/IIIT5K/test/261_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AIRPORT",
|
|
"image_path": "./data/IIIT5K/test/261_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANGALORE",
|
|
"image_path": "./data/IIIT5K/test/261_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HYDERABAD",
|
|
"image_path": "./data/IIIT5K/test/261_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROAD",
|
|
"image_path": "./data/IIIT5K/test/2621_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOLENT",
|
|
"image_path": "./data/IIIT5K/test/2621_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "view",
|
|
"gt_answers": "VIEW",
|
|
"image_path": "./data/IIIT5K/test/2621_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "123",
|
|
"image_path": "./data/IIIT5K/test/2621_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONE",
|
|
"image_path": "./data/IIIT5K/test/2621_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "58",
|
|
"image_path": "./data/IIIT5K/test/2621_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "church",
|
|
"gt_answers": "CHRUCH",
|
|
"image_path": "./data/IIIT5K/test/2621_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OVAL",
|
|
"image_path": "./data/IIIT5K/test/2622_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NUMBER",
|
|
"image_path": "./data/IIIT5K/test/2622_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PLAQUE",
|
|
"image_path": "./data/IIIT5K/test/2622_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VISTA",
|
|
"image_path": "./data/IIIT5K/test/2624_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "4",
|
|
"image_path": "./data/IIIT5K/test/2624_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HARDWICK",
|
|
"image_path": "./data/IIIT5K/test/2624_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2624_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OLD",
|
|
"image_path": "./data/IIIT5K/test/2624_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COTTAGE",
|
|
"image_path": "./data/IIIT5K/test/2624_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LEA",
|
|
"image_path": "./data/IIIT5K/test/2624_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HALE",
|
|
"image_path": "./data/IIIT5K/test/2624_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "227",
|
|
"image_path": "./data/IIIT5K/test/2624_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOUNDRY",
|
|
"image_path": "./data/IIIT5K/test/2624_25.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LANE",
|
|
"image_path": "./data/IIIT5K/test/2624_26.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "38A",
|
|
"image_path": "./data/IIIT5K/test/2624_30.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "7",
|
|
"gt_answers": "7",
|
|
"image_path": "./data/IIIT5K/test/2624_32.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "meadows",
|
|
"gt_answers": "MEADOWS",
|
|
"image_path": "./data/IIIT5K/test/2624_33.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MILLVIEW",
|
|
"image_path": "./data/IIIT5K/test/2624_34.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "12",
|
|
"image_path": "./data/IIIT5K/test/2624_35.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "30",
|
|
"image_path": "./data/IIIT5K/test/2624_36.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEMBURY",
|
|
"image_path": "./data/IIIT5K/test/2624_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "villas",
|
|
"gt_answers": "VILLAS",
|
|
"image_path": "./data/IIIT5K/test/2624_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALEXANDER",
|
|
"image_path": "./data/IIIT5K/test/2624_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/2624_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FAILTE",
|
|
"image_path": "./data/IIIT5K/test/2625_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/2626_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "magpies",
|
|
"gt_answers": "MAGPIES",
|
|
"image_path": "./data/IIIT5K/test/2626_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIMPLY",
|
|
"image_path": "./data/IIIT5K/test/2626_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "90",
|
|
"image_path": "./data/IIIT5K/test/263_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "97",
|
|
"image_path": "./data/IIIT5K/test/263_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NAHRUNGSERGANZUNG",
|
|
"image_path": "./data/IIIT5K/test/264_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HANTECH",
|
|
"image_path": "./data/IIIT5K/test/26_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAUTIONARY",
|
|
"image_path": "./data/IIIT5K/test/26_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGNS",
|
|
"image_path": "./data/IIIT5K/test/26_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EN",
|
|
"image_path": "./data/IIIT5K/test/272_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/272_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWW",
|
|
"image_path": "./data/IIIT5K/test/272_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRST",
|
|
"image_path": "./data/IIIT5K/test/272_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/272_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/273_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PARKING",
|
|
"image_path": "./data/IIIT5K/test/273_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bluetooth",
|
|
"gt_answers": "BLUETOOTH",
|
|
"image_path": "./data/IIIT5K/test/276_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "marketing",
|
|
"gt_answers": "MARKETING",
|
|
"image_path": "./data/IIIT5K/test/276_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEVICE",
|
|
"image_path": "./data/IIIT5K/test/276_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRO",
|
|
"image_path": "./data/IIIT5K/test/276_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hot",
|
|
"gt_answers": "HOT",
|
|
"image_path": "./data/IIIT5K/test/276_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "exit",
|
|
"gt_answers": "EXIT",
|
|
"image_path": "./data/IIIT5K/test/278_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLY",
|
|
"image_path": "./data/IIIT5K/test/278_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "6279",
|
|
"image_path": "./data/IIIT5K/test/279_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/27_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/27_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/27_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOURS",
|
|
"image_path": "./data/IIIT5K/test/281_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "600PM",
|
|
"image_path": "./data/IIIT5K/test/281_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SATURDAY",
|
|
"image_path": "./data/IIIT5K/test/281_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "900AM",
|
|
"image_path": "./data/IIIT5K/test/281_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1200PM",
|
|
"image_path": "./data/IIIT5K/test/281_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "operation",
|
|
"gt_answers": "OPERATION",
|
|
"image_path": "./data/IIIT5K/test/281_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MONDAY",
|
|
"image_path": "./data/IIIT5K/test/281_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THURSDAY",
|
|
"image_path": "./data/IIIT5K/test/281_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "900AM",
|
|
"image_path": "./data/IIIT5K/test/281_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "500PM",
|
|
"image_path": "./data/IIIT5K/test/281_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "friday",
|
|
"gt_answers": "FRIDAY",
|
|
"image_path": "./data/IIIT5K/test/281_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DICOLOR",
|
|
"image_path": "./data/IIIT5K/test/282_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLY",
|
|
"image_path": "./data/IIIT5K/test/285_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/285_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHENNAI",
|
|
"image_path": "./data/IIIT5K/test/285_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FRESH",
|
|
"image_path": "./data/IIIT5K/test/288_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FRUIT",
|
|
"image_path": "./data/IIIT5K/test/288_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIBABA",
|
|
"image_path": "./data/IIIT5K/test/289_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "proud",
|
|
"gt_answers": "PROUD",
|
|
"image_path": "./data/IIIT5K/test/28_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/28_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BE",
|
|
"image_path": "./data/IIIT5K/test/28_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "indian",
|
|
"gt_answers": "INDIAN",
|
|
"image_path": "./data/IIIT5K/test/28_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "H",
|
|
"image_path": "./data/IIIT5K/test/290_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "K",
|
|
"image_path": "./data/IIIT5K/test/290_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "S",
|
|
"image_path": "./data/IIIT5K/test/290_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "drft",
|
|
"gt_answers": "DRFT",
|
|
"image_path": "./data/IIIT5K/test/290_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "please",
|
|
"gt_answers": "PLEASE",
|
|
"image_path": "./data/IIIT5K/test/291_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/291_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COCKROACHES",
|
|
"image_path": "./data/IIIT5K/test/291_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARE",
|
|
"image_path": "./data/IIIT5K/test/291_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GETTING",
|
|
"image_path": "./data/IIIT5K/test/291_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cancer",
|
|
"gt_answers": "CANCER",
|
|
"image_path": "./data/IIIT5K/test/291_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "throw",
|
|
"gt_answers": "THROW",
|
|
"image_path": "./data/IIIT5K/test/291_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/291_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CIGARETTE",
|
|
"image_path": "./data/IIIT5K/test/291_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ENDS",
|
|
"image_path": "./data/IIIT5K/test/291_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/291_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/291_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EYE",
|
|
"image_path": "./data/IIIT5K/test/294_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/294_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MALAYSIA",
|
|
"image_path": "./data/IIIT5K/test/294_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/295_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VACANT",
|
|
"image_path": "./data/IIIT5K/test/296_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AVAILABLE",
|
|
"image_path": "./data/IIIT5K/test/296_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/296_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CALL",
|
|
"image_path": "./data/IIIT5K/test/296_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "0800",
|
|
"image_path": "./data/IIIT5K/test/296_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/296_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EAT",
|
|
"image_path": "./data/IIIT5K/test/297_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOR",
|
|
"image_path": "./data/IIIT5K/test/297_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHIKIN",
|
|
"image_path": "./data/IIIT5K/test/297_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IPAD",
|
|
"image_path": "./data/IIIT5K/test/29_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VECTOR",
|
|
"image_path": "./data/IIIT5K/test/305_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "smog",
|
|
"gt_answers": "SMOG",
|
|
"image_path": "./data/IIIT5K/test/306_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALERT",
|
|
"image_path": "./data/IIIT5K/test/306_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REDUCE",
|
|
"image_path": "./data/IIIT5K/test/306_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VEHICLE",
|
|
"image_path": "./data/IIIT5K/test/306_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "use",
|
|
"gt_answers": "USE",
|
|
"image_path": "./data/IIIT5K/test/306_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "masterfile",
|
|
"gt_answers": "MASTERFILE",
|
|
"image_path": "./data/IIIT5K/test/306_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "masterfile",
|
|
"gt_answers": "MASTERFILE",
|
|
"image_path": "./data/IIIT5K/test/307_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MASTERFILE",
|
|
"image_path": "./data/IIIT5K/test/308_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/30_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the glades",
|
|
"gt_answers": "GLADES",
|
|
"image_path": "./data/IIIT5K/test/30_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/30_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOMICIDE",
|
|
"image_path": "./data/IIIT5K/test/30_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FREE",
|
|
"image_path": "./data/IIIT5K/test/30_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "drink",
|
|
"gt_answers": "DRINK",
|
|
"image_path": "./data/IIIT5K/test/310_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/310_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/310_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANGKOK",
|
|
"image_path": "./data/IIIT5K/test/310_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REDVIEW",
|
|
"image_path": "./data/IIIT5K/test/311_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GPS",
|
|
"image_path": "./data/IIIT5K/test/311_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TRAC",
|
|
"image_path": "./data/IIIT5K/test/311_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "redview",
|
|
"gt_answers": "REDVIEW",
|
|
"image_path": "./data/IIIT5K/test/311_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALUONTOP",
|
|
"image_path": "./data/IIIT5K/test/312_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWVTRJTCOM",
|
|
"image_path": "./data/IIIT5K/test/319_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORLD",
|
|
"image_path": "./data/IIIT5K/test/31_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "off",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/31_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "color",
|
|
"gt_answers": "COLOR",
|
|
"image_path": "./data/IIIT5K/test/31_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/31_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "water",
|
|
"gt_answers": "WATER",
|
|
"image_path": "./data/IIIT5K/test/31_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "spectacular",
|
|
"gt_answers": "SPECTACULAR",
|
|
"image_path": "./data/IIIT5K/test/31_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HANDY",
|
|
"image_path": "./data/IIIT5K/test/321_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOG",
|
|
"image_path": "./data/IIIT5K/test/321_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGN",
|
|
"image_path": "./data/IIIT5K/test/321_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/321_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JUNK",
|
|
"image_path": "./data/IIIT5K/test/321_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAIL",
|
|
"image_path": "./data/IIIT5K/test/321_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGN",
|
|
"image_path": "./data/IIIT5K/test/321_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ladies",
|
|
"gt_answers": "LADIES",
|
|
"image_path": "./data/IIIT5K/test/321_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shoes",
|
|
"gt_answers": "SHOES",
|
|
"image_path": "./data/IIIT5K/test/321_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OFF",
|
|
"image_path": "./data/IIIT5K/test/321_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "please",
|
|
"gt_answers": "PLEASE",
|
|
"image_path": "./data/IIIT5K/test/321_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HANDY",
|
|
"image_path": "./data/IIIT5K/test/321_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEWARE",
|
|
"image_path": "./data/IIIT5K/test/321_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LED",
|
|
"image_path": "./data/IIIT5K/test/322_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/323_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIFE",
|
|
"image_path": "./data/IIIT5K/test/323_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "aa",
|
|
"gt_answers": "AAA",
|
|
"image_path": "./data/IIIT5K/test/323_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CRISIL",
|
|
"image_path": "./data/IIIT5K/test/323_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/323_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIFE",
|
|
"image_path": "./data/IIIT5K/test/323_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "green",
|
|
"gt_answers": "GREEN",
|
|
"image_path": "./data/IIIT5K/test/325_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/325_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PER",
|
|
"image_path": "./data/IIIT5K/test/325_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WEEK",
|
|
"image_path": "./data/IIIT5K/test/325_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOOK",
|
|
"image_path": "./data/IIIT5K/test/325_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PEDITRI",
|
|
"image_path": "./data/IIIT5K/test/325_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNIT",
|
|
"image_path": "./data/IIIT5K/test/325_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MANY",
|
|
"image_path": "./data/IIIT5K/test/325_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/325_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THESE",
|
|
"image_path": "./data/IIIT5K/test/325_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/325_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CUSTOMERS",
|
|
"image_path": "./data/IIIT5K/test/325_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KNOW",
|
|
"image_path": "./data/IIIT5K/test/325_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ABOUT",
|
|
"image_path": "./data/IIIT5K/test/325_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUSINESS",
|
|
"image_path": "./data/IIIT5K/test/325_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/325_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADS",
|
|
"image_path": "./data/IIIT5K/test/325_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/325_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AD",
|
|
"image_path": "./data/IIIT5K/test/325_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/325_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "15HR",
|
|
"image_path": "./data/IIIT5K/test/325_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/326_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/326_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/326_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/326_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "START",
|
|
"image_path": "./data/IIIT5K/test/328_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IMPACT",
|
|
"image_path": "./data/IIIT5K/test/328_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "and and",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/328_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REACH",
|
|
"image_path": "./data/IIIT5K/test/328_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MASS",
|
|
"image_path": "./data/IIIT5K/test/328_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AUDIENCES",
|
|
"image_path": "./data/IIIT5K/test/328_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COST",
|
|
"image_path": "./data/IIIT5K/test/328_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADVERTISE",
|
|
"image_path": "./data/IIIT5K/test/328_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WITH",
|
|
"image_path": "./data/IIIT5K/test/328_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "US",
|
|
"image_path": "./data/IIIT5K/test/328_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TODAY",
|
|
"image_path": "./data/IIIT5K/test/328_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "9546388443",
|
|
"image_path": "./data/IIIT5K/test/328_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUSINESS",
|
|
"image_path": "./data/IIIT5K/test/328_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/328_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is your name",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/328_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMPANY",
|
|
"image_path": "./data/IIIT5K/test/328_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "create",
|
|
"gt_answers": "CREATE",
|
|
"image_path": "./data/IIIT5K/test/328_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/328_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/329_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/329_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AS",
|
|
"image_path": "./data/IIIT5K/test/329_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOW",
|
|
"image_path": "./data/IIIT5K/test/329_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AS",
|
|
"image_path": "./data/IIIT5K/test/329_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/329_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5612812394",
|
|
"image_path": "./data/IIIT5K/test/329_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "available soon",
|
|
"gt_answers": "AVAILABLE",
|
|
"image_path": "./data/IIIT5K/test/32_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "adoption",
|
|
"gt_answers": "ADOPTION",
|
|
"image_path": "./data/IIIT5K/test/32_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pramukh",
|
|
"gt_answers": "PRAMUKH",
|
|
"image_path": "./data/IIIT5K/test/330_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GLOW",
|
|
"image_path": "./data/IIIT5K/test/330_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGN",
|
|
"image_path": "./data/IIIT5K/test/330_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "happy birthday",
|
|
"gt_answers": "HAPPY",
|
|
"image_path": "./data/IIIT5K/test/331_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is stop",
|
|
"gt_answers": "STOP",
|
|
"image_path": "./data/IIIT5K/test/332_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "skateboarders",
|
|
"gt_answers": "SKATEBOARDERS",
|
|
"image_path": "./data/IIIT5K/test/333_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1972",
|
|
"image_path": "./data/IIIT5K/test/333_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "heaven",
|
|
"gt_answers": "HEAVEN",
|
|
"image_path": "./data/IIIT5K/test/334_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hell",
|
|
"gt_answers": "HELL",
|
|
"image_path": "./data/IIIT5K/test/334_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWCLIPARTOFCOM50027",
|
|
"image_path": "./data/IIIT5K/test/337_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CRESTOCK",
|
|
"image_path": "./data/IIIT5K/test/338_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/338_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/339_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/339_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/339_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/339_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AIRTEL",
|
|
"image_path": "./data/IIIT5K/test/339_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "coca cola",
|
|
"gt_answers": "COCACOLA",
|
|
"image_path": "./data/IIIT5K/test/33_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/33_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "coke",
|
|
"gt_answers": "COKE",
|
|
"image_path": "./data/IIIT5K/test/33_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "side",
|
|
"gt_answers": "SIDE",
|
|
"image_path": "./data/IIIT5K/test/33_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/33_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "life",
|
|
"gt_answers": "LIFE",
|
|
"image_path": "./data/IIIT5K/test/33_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "clear channel",
|
|
"gt_answers": "CLEARCHANNEL",
|
|
"image_path": "./data/IIIT5K/test/33_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THANK",
|
|
"image_path": "./data/IIIT5K/test/340_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "U",
|
|
"image_path": "./data/IIIT5K/test/340_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHUTTERSTOCK",
|
|
"image_path": "./data/IIIT5K/test/340_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWSHUTTERSTOCKCOM",
|
|
"image_path": "./data/IIIT5K/test/340_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "55496002",
|
|
"image_path": "./data/IIIT5K/test/340_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is written in the image",
|
|
"gt_answers": "SHUTTERSTOCK",
|
|
"image_path": "./data/IIIT5K/test/348_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWSHUTTERSTOCKCOM",
|
|
"image_path": "./data/IIIT5K/test/348_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "45367396",
|
|
"image_path": "./data/IIIT5K/test/348_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WHATS",
|
|
"image_path": "./data/IIIT5K/test/34_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/34_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANQUET",
|
|
"image_path": "./data/IIIT5K/test/34_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OR",
|
|
"image_path": "./data/IIIT5K/test/34_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BIG",
|
|
"image_path": "./data/IIIT5K/test/34_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FAT",
|
|
"image_path": "./data/IIIT5K/test/34_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BIRD",
|
|
"image_path": "./data/IIIT5K/test/34_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ABOUT",
|
|
"image_path": "./data/IIIT5K/test/34_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/34_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HIT",
|
|
"image_path": "./data/IIIT5K/test/34_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/34_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGNBOARD",
|
|
"image_path": "./data/IIIT5K/test/34_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ITS",
|
|
"image_path": "./data/IIIT5K/test/34_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EITHER",
|
|
"image_path": "./data/IIIT5K/test/34_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/34_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMING",
|
|
"image_path": "./data/IIIT5K/test/34_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/34_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/34_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWSHUTTERSTOCKCOM",
|
|
"image_path": "./data/IIIT5K/test/353_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "46143994",
|
|
"image_path": "./data/IIIT5K/test/353_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is democracy",
|
|
"gt_answers": "DEMOCRAT",
|
|
"image_path": "./data/IIIT5K/test/357_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/357_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOARD",
|
|
"image_path": "./data/IIIT5K/test/357_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWSHUTTERSTOCKCOM",
|
|
"image_path": "./data/IIIT5K/test/357_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/358_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bank",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/358_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/358_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/358_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAY",
|
|
"image_path": "./data/IIIT5K/test/360_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2",
|
|
"image_path": "./data/IIIT5K/test/360_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOING",
|
|
"image_path": "./data/IIIT5K/test/360_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOOGLE",
|
|
"image_path": "./data/IIIT5K/test/360_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEANS",
|
|
"image_path": "./data/IIIT5K/test/360_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "switching",
|
|
"gt_answers": "SWITCHING",
|
|
"image_path": "./data/IIIT5K/test/360_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/360_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOOGLE",
|
|
"image_path": "./data/IIIT5K/test/360_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DART",
|
|
"image_path": "./data/IIIT5K/test/361_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPEN",
|
|
"image_path": "./data/IIIT5K/test/363_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STORE",
|
|
"image_path": "./data/IIIT5K/test/363_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/363_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "507719",
|
|
"image_path": "./data/IIIT5K/test/363_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIP",
|
|
"image_path": "./data/IIIT5K/test/366_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "008",
|
|
"image_path": "./data/IIIT5K/test/366_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SMOKING",
|
|
"image_path": "./data/IIIT5K/test/367_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shop",
|
|
"gt_answers": "SHOP",
|
|
"image_path": "./data/IIIT5K/test/367_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "stores",
|
|
"gt_answers": "STORES",
|
|
"image_path": "./data/IIIT5K/test/367_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shop",
|
|
"gt_answers": "SHOP",
|
|
"image_path": "./data/IIIT5K/test/367_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "stores",
|
|
"gt_answers": "STORES",
|
|
"image_path": "./data/IIIT5K/test/367_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RESTROOMS",
|
|
"image_path": "./data/IIIT5K/test/367_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OFFICE",
|
|
"image_path": "./data/IIIT5K/test/367_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bathrooms",
|
|
"gt_answers": "RESTROOMS",
|
|
"image_path": "./data/IIIT5K/test/367_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RESTROOMS",
|
|
"image_path": "./data/IIIT5K/test/367_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/367_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shop",
|
|
"gt_answers": "SHOP",
|
|
"image_path": "./data/IIIT5K/test/367_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KFC",
|
|
"image_path": "./data/IIIT5K/test/370_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hot",
|
|
"gt_answers": "HOT",
|
|
"image_path": "./data/IIIT5K/test/370_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2003",
|
|
"image_path": "./data/IIIT5K/test/377_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FT",
|
|
"image_path": "./data/IIIT5K/test/377_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MYERS",
|
|
"image_path": "./data/IIIT5K/test/377_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "research",
|
|
"gt_answers": "RESEARCH",
|
|
"image_path": "./data/IIIT5K/test/377_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/377_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IMPROVEMENT",
|
|
"image_path": "./data/IIIT5K/test/377_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/37_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "geico",
|
|
"gt_answers": "GEICO",
|
|
"image_path": "./data/IIIT5K/test/37_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "direct",
|
|
"gt_answers": "DIRECT",
|
|
"image_path": "./data/IIIT5K/test/37_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AUTO",
|
|
"image_path": "./data/IIIT5K/test/37_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INSURANCE",
|
|
"image_path": "./data/IIIT5K/test/37_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "15",
|
|
"gt_answers": "15",
|
|
"image_path": "./data/IIIT5K/test/37_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MINUTE",
|
|
"image_path": "./data/IIIT5K/test/37_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "call",
|
|
"gt_answers": "CALL",
|
|
"image_path": "./data/IIIT5K/test/37_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COULD",
|
|
"image_path": "./data/IIIT5K/test/37_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/37_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "15",
|
|
"image_path": "./data/IIIT5K/test/37_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1800GOGEICO",
|
|
"image_path": "./data/IIIT5K/test/37_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TP",
|
|
"image_path": "./data/IIIT5K/test/385_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "02",
|
|
"image_path": "./data/IIIT5K/test/385_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cursed",
|
|
"gt_answers": "CURSED",
|
|
"image_path": "./data/IIIT5K/test/386_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CARIBBE",
|
|
"image_path": "./data/IIIT5K/test/386_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FANDOM",
|
|
"image_path": "./data/IIIT5K/test/386_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EST",
|
|
"image_path": "./data/IIIT5K/test/386_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "royalty",
|
|
"gt_answers": "REGENCY",
|
|
"image_path": "./data/IIIT5K/test/38_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAUTION",
|
|
"image_path": "./data/IIIT5K/test/390_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YELLOW",
|
|
"image_path": "./data/IIIT5K/test/390_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STOP",
|
|
"image_path": "./data/IIIT5K/test/391_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/392_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/392_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/392_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROAD",
|
|
"image_path": "./data/IIIT5K/test/393_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHOW",
|
|
"image_path": "./data/IIIT5K/test/395_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "time",
|
|
"gt_answers": "TIME",
|
|
"image_path": "./data/IIIT5K/test/395_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "special",
|
|
"gt_answers": "SPECIAL",
|
|
"image_path": "./data/IIIT5K/test/395_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TODAY",
|
|
"image_path": "./data/IIIT5K/test/395_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ERCITING",
|
|
"image_path": "./data/IIIT5K/test/395_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "what is written in the image",
|
|
"gt_answers": "MENUBOARD",
|
|
"image_path": "./data/IIIT5K/test/395_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/398_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/398_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/399_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAKE",
|
|
"image_path": "./data/IIIT5K/test/3_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/3_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MESSAGE",
|
|
"image_path": "./data/IIIT5K/test/3_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mobile",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/3_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/401_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/401_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/401_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/401_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "airtel",
|
|
"gt_answers": "AIRTEL",
|
|
"image_path": "./data/IIIT5K/test/402_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAST",
|
|
"image_path": "./data/IIIT5K/test/403_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DATE",
|
|
"image_path": "./data/IIIT5K/test/403_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1ST",
|
|
"image_path": "./data/IIIT5K/test/403_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/403_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/403_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/403_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "6100",
|
|
"image_path": "./data/IIIT5K/test/403_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WEEKS",
|
|
"image_path": "./data/IIIT5K/test/405_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RECOMMENDED",
|
|
"image_path": "./data/IIIT5K/test/405_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/405_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the jersey shore",
|
|
"gt_answers": "JERSEY",
|
|
"image_path": "./data/IIIT5K/test/405_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLEARCHANNEL",
|
|
"image_path": "./data/IIIT5K/test/405_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BACKPACK",
|
|
"image_path": "./data/IIIT5K/test/406_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARDS",
|
|
"image_path": "./data/IIIT5K/test/406_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TEXT",
|
|
"image_path": "./data/IIIT5K/test/406_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5683",
|
|
"image_path": "./data/IIIT5K/test/406_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWLOUDBILLBOARDSCOM",
|
|
"image_path": "./data/IIIT5K/test/406_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "grass roots marketing",
|
|
"gt_answers": "GRASSROOTSMARKETING",
|
|
"image_path": "./data/IIIT5K/test/406_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/406_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/406_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "trucks",
|
|
"gt_answers": "TRUCKS",
|
|
"image_path": "./data/IIIT5K/test/406_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TWIN",
|
|
"image_path": "./data/IIIT5K/test/407_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "peaks",
|
|
"gt_answers": "PEAKS",
|
|
"image_path": "./data/IIIT5K/test/407_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOPARKING",
|
|
"image_path": "./data/IIIT5K/test/40_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UTURN",
|
|
"image_path": "./data/IIIT5K/test/40_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOSTOPPING",
|
|
"image_path": "./data/IIIT5K/test/40_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "no standing",
|
|
"gt_answers": "NOSTANDING",
|
|
"image_path": "./data/IIIT5K/test/40_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PROHIBITED",
|
|
"image_path": "./data/IIIT5K/test/40_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OVERTAKING",
|
|
"image_path": "./data/IIIT5K/test/40_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PROHIBITED",
|
|
"image_path": "./data/IIIT5K/test/40_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SPEEDLIMIT",
|
|
"image_path": "./data/IIIT5K/test/40_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twin",
|
|
"gt_answers": "TWIN",
|
|
"image_path": "./data/IIIT5K/test/410_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "peaks",
|
|
"gt_answers": "PEAKS",
|
|
"image_path": "./data/IIIT5K/test/410_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "53327",
|
|
"image_path": "./data/IIIT5K/test/411_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fireworks",
|
|
"gt_answers": "FIREWORKS",
|
|
"image_path": "./data/IIIT5K/test/411_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ESCAPE",
|
|
"image_path": "./data/IIIT5K/test/412_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/412_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "join the crowds",
|
|
"gt_answers": "CROWDS",
|
|
"image_path": "./data/IIIT5K/test/412_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AUCTION",
|
|
"image_path": "./data/IIIT5K/test/413_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "7023083507",
|
|
"image_path": "./data/IIIT5K/test/414_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/415_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IPOHCHAICOM",
|
|
"image_path": "./data/IIIT5K/test/415_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/415_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/415_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NARROW",
|
|
"image_path": "./data/IIIT5K/test/415_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOH",
|
|
"image_path": "./data/IIIT5K/test/415_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/418_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/418_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAY2008",
|
|
"image_path": "./data/IIIT5K/test/419_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/419_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/419_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/419_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LILLIPUT",
|
|
"image_path": "./data/IIIT5K/test/41_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "billboard",
|
|
"gt_answers": "BILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/421_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "6",
|
|
"image_path": "./data/IIIT5K/test/424_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KOLBY",
|
|
"image_path": "./data/IIIT5K/test/424_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KAS",
|
|
"image_path": "./data/IIIT5K/test/424_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3",
|
|
"image_path": "./data/IIIT5K/test/424_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PILLEMARK",
|
|
"image_path": "./data/IIIT5K/test/424_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "K",
|
|
"image_path": "./data/IIIT5K/test/425_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "psychic",
|
|
"gt_answers": "PSYCHIC",
|
|
"image_path": "./data/IIIT5K/test/426_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ITS",
|
|
"image_path": "./data/IIIT5K/test/427_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YNB",
|
|
"image_path": "./data/IIIT5K/test/427_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fashionista",
|
|
"gt_answers": "FASHIONISTAS",
|
|
"image_path": "./data/IIIT5K/test/429_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MARINES",
|
|
"image_path": "./data/IIIT5K/test/431_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/431_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "forever",
|
|
"gt_answers": "FOREVER",
|
|
"image_path": "./data/IIIT5K/test/431_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/433_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANKING",
|
|
"image_path": "./data/IIIT5K/test/433_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "food outlet",
|
|
"gt_answers": "OUTLET",
|
|
"image_path": "./data/IIIT5K/test/435_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "goodwill",
|
|
"gt_answers": "GOODWILL",
|
|
"image_path": "./data/IIIT5K/test/435_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PENINJAU",
|
|
"image_path": "./data/IIIT5K/test/439_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "4",
|
|
"gt_answers": "4",
|
|
"image_path": "./data/IIIT5K/test/439_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KM",
|
|
"image_path": "./data/IIIT5K/test/439_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "01922",
|
|
"image_path": "./data/IIIT5K/test/440_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "745",
|
|
"image_path": "./data/IIIT5K/test/440_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "604",
|
|
"gt_answers": "604",
|
|
"image_path": "./data/IIIT5K/test/440_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "construction",
|
|
"gt_answers": "CONSTRUCTION",
|
|
"image_path": "./data/IIIT5K/test/440_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ltd",
|
|
"gt_answers": "LTD",
|
|
"image_path": "./data/IIIT5K/test/440_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tel",
|
|
"gt_answers": "TEL",
|
|
"image_path": "./data/IIIT5K/test/440_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/444_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHECKING",
|
|
"image_path": "./data/IIIT5K/test/444_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ACCOUNT",
|
|
"image_path": "./data/IIIT5K/test/444_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/455_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/455_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/455_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOOD",
|
|
"image_path": "./data/IIIT5K/test/45_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LUCK",
|
|
"image_path": "./data/IIIT5K/test/45_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "45",
|
|
"gt_answers": "45",
|
|
"image_path": "./data/IIIT5K/test/45_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MPH",
|
|
"image_path": "./data/IIIT5K/test/45_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wraps",
|
|
"gt_answers": "WRAPS",
|
|
"image_path": "./data/IIIT5K/test/4_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "lettering",
|
|
"gt_answers": "LETTERING",
|
|
"image_path": "./data/IIIT5K/test/4_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAGNETICS",
|
|
"image_path": "./data/IIIT5K/test/4_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALSO",
|
|
"image_path": "./data/IIIT5K/test/4_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AVAILABLE",
|
|
"image_path": "./data/IIIT5K/test/4_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/5000_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THEM",
|
|
"image_path": "./data/IIIT5K/test/5000_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUSINESS",
|
|
"image_path": "./data/IIIT5K/test/5000_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEN",
|
|
"image_path": "./data/IIIT5K/test/5000_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LEGACY",
|
|
"image_path": "./data/IIIT5K/test/5001_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREEN",
|
|
"image_path": "./data/IIIT5K/test/5002_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LANTERN",
|
|
"image_path": "./data/IIIT5K/test/5002_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JUNE",
|
|
"image_path": "./data/IIIT5K/test/5002_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "17",
|
|
"gt_answers": "17",
|
|
"image_path": "./data/IIIT5K/test/5002_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORLD",
|
|
"image_path": "./data/IIIT5K/test/5003_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/5003_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOT",
|
|
"image_path": "./data/IIIT5K/test/5003_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "what is written in the image",
|
|
"gt_answers": "ENOUGH",
|
|
"image_path": "./data/IIIT5K/test/5003_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5004_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "divide",
|
|
"gt_answers": "DIVIDE",
|
|
"image_path": "./data/IIIT5K/test/5004_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THOR",
|
|
"image_path": "./data/IIIT5K/test/5006_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MARILYN",
|
|
"image_path": "./data/IIIT5K/test/5007_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GEORGE",
|
|
"image_path": "./data/IIIT5K/test/5007_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AXELROD",
|
|
"image_path": "./data/IIIT5K/test/5007_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STOP",
|
|
"image_path": "./data/IIIT5K/test/5007_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DON",
|
|
"image_path": "./data/IIIT5K/test/5007_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MURRAY",
|
|
"image_path": "./data/IIIT5K/test/5007_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AUDREY",
|
|
"image_path": "./data/IIIT5K/test/5008_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FACE",
|
|
"image_path": "./data/IIIT5K/test/5008_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REST",
|
|
"image_path": "./data/IIIT5K/test/5009_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/5009_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CURTIS",
|
|
"image_path": "./data/IIIT5K/test/5010_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "50",
|
|
"image_path": "./data/IIIT5K/test/5010_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CENT",
|
|
"image_path": "./data/IIIT5K/test/5010_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gun",
|
|
"gt_answers": "GUN",
|
|
"image_path": "./data/IIIT5K/test/5010_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REEVES",
|
|
"image_path": "./data/IIIT5K/test/5011_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAURENCE",
|
|
"image_path": "./data/IIIT5K/test/5011_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FISHBURNE",
|
|
"image_path": "./data/IIIT5K/test/5011_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/5012_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIN",
|
|
"image_path": "./data/IIIT5K/test/5012_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CITY",
|
|
"image_path": "./data/IIIT5K/test/5012_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THOR",
|
|
"image_path": "./data/IIIT5K/test/5013_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "limitless",
|
|
"gt_answers": "LIMITLESS",
|
|
"image_path": "./data/IIIT5K/test/5014_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "shanghai",
|
|
"gt_answers": "SHANGHAI",
|
|
"image_path": "./data/IIIT5K/test/5015_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMING",
|
|
"image_path": "./data/IIIT5K/test/5016_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOON",
|
|
"image_path": "./data/IIIT5K/test/5016_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IM",
|
|
"image_path": "./data/IIIT5K/test/5017_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HEATH",
|
|
"image_path": "./data/IIIT5K/test/5017_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LEDGER",
|
|
"image_path": "./data/IIIT5K/test/5017_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEN",
|
|
"image_path": "./data/IIIT5K/test/5017_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CATE",
|
|
"image_path": "./data/IIIT5K/test/5017_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BLANCHETT",
|
|
"image_path": "./data/IIIT5K/test/5017_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MARCUS",
|
|
"image_path": "./data/IIIT5K/test/5017_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nations",
|
|
"gt_answers": "NATIONS",
|
|
"image_path": "./data/IIIT5K/test/5018_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "destiny",
|
|
"gt_answers": "DESTINEE",
|
|
"image_path": "./data/IIIT5K/test/5018_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "3d",
|
|
"gt_answers": "3D",
|
|
"image_path": "./data/IIIT5K/test/5019_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "action",
|
|
"gt_answers": "ACTION",
|
|
"image_path": "./data/IIIT5K/test/5019_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLINT",
|
|
"image_path": "./data/IIIT5K/test/5020_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/5020_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "eastwood",
|
|
"gt_answers": "EASTWOOD",
|
|
"image_path": "./data/IIIT5K/test/5020_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/5020_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WHO",
|
|
"image_path": "./data/IIIT5K/test/5020_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "learn and grow",
|
|
"gt_answers": "LEARNS",
|
|
"image_path": "./data/IIIT5K/test/5020_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GERARO",
|
|
"image_path": "./data/IIIT5K/test/5022_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUTLER",
|
|
"image_path": "./data/IIIT5K/test/5022_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gamer",
|
|
"gt_answers": "GAMER",
|
|
"image_path": "./data/IIIT5K/test/5022_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "secretariat",
|
|
"gt_answers": "SECRETARIAT",
|
|
"image_path": "./data/IIIT5K/test/5023_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "love",
|
|
"gt_answers": "LOVE",
|
|
"image_path": "./data/IIIT5K/test/5024_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wynton kern and a book",
|
|
"gt_answers": "WYNTON",
|
|
"image_path": "./data/IIIT5K/test/5024_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "marsalis",
|
|
"gt_answers": "MARSALIS",
|
|
"image_path": "./data/IIIT5K/test/5024_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CECILE",
|
|
"image_path": "./data/IIIT5K/test/5024_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LICAD",
|
|
"image_path": "./data/IIIT5K/test/5024_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/5024_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DREAMS",
|
|
"image_path": "./data/IIIT5K/test/5024_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ORLEANS",
|
|
"image_path": "./data/IIIT5K/test/5024_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "louis",
|
|
"gt_answers": "LOUIS",
|
|
"image_path": "./data/IIIT5K/test/5024_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SILENT",
|
|
"image_path": "./data/IIIT5K/test/5024_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/5025_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mind",
|
|
"gt_answers": "MIND",
|
|
"image_path": "./data/IIIT5K/test/5025_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "blowing",
|
|
"gt_answers": "BLOWING",
|
|
"image_path": "./data/IIIT5K/test/5025_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "stone",
|
|
"gt_answers": "STONE",
|
|
"image_path": "./data/IIIT5K/test/5026_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NORTON",
|
|
"image_path": "./data/IIIT5K/test/5026_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nero",
|
|
"gt_answers": "NIRO",
|
|
"image_path": "./data/IIIT5K/test/5026_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WILLIS",
|
|
"image_path": "./data/IIIT5K/test/5027_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RETRAITE",
|
|
"image_path": "./data/IIIT5K/test/5027_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "red",
|
|
"gt_answers": "RED",
|
|
"image_path": "./data/IIIT5K/test/5027_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RETRAITES",
|
|
"image_path": "./data/IIIT5K/test/5027_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXTREMEMENT",
|
|
"image_path": "./data/IIIT5K/test/5027_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMEDIE",
|
|
"image_path": "./data/IIIT5K/test/5027_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "explosive",
|
|
"gt_answers": "EXPLOSIVE",
|
|
"image_path": "./data/IIIT5K/test/5027_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SUR",
|
|
"image_path": "./data/IIIT5K/test/5027_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SAW",
|
|
"image_path": "./data/IIIT5K/test/5028_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ACTIVITY",
|
|
"image_path": "./data/IIIT5K/test/5028_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MUSIC",
|
|
"image_path": "./data/IIIT5K/test/5029_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WASHINGTON",
|
|
"image_path": "./data/IIIT5K/test/5030_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "chris brown",
|
|
"gt_answers": "CHRIS",
|
|
"image_path": "./data/IIIT5K/test/5030_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PINE",
|
|
"image_path": "./data/IIIT5K/test/5030_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "november",
|
|
"gt_answers": "NOVEMBER",
|
|
"image_path": "./data/IIIT5K/test/5030_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIFE",
|
|
"image_path": "./data/IIIT5K/test/5031_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AQUATIC",
|
|
"image_path": "./data/IIIT5K/test/5031_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STEVE",
|
|
"image_path": "./data/IIIT5K/test/5031_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "alien",
|
|
"gt_answers": "ALIEN",
|
|
"image_path": "./data/IIIT5K/test/5036_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/5036_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SPACE",
|
|
"image_path": "./data/IIIT5K/test/5036_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/5036_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SCREAM",
|
|
"image_path": "./data/IIIT5K/test/5036_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "it takes a legend",
|
|
"gt_answers": "LEGEND",
|
|
"image_path": "./data/IIIT5K/test/5037_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STAR",
|
|
"image_path": "./data/IIIT5K/test/5037_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TERRIFYING",
|
|
"image_path": "./data/IIIT5K/test/5038_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hard",
|
|
"gt_answers": "HARD",
|
|
"image_path": "./data/IIIT5K/test/5038_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "candy",
|
|
"gt_answers": "CANDY",
|
|
"image_path": "./data/IIIT5K/test/5038_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "black",
|
|
"gt_answers": "BLACK",
|
|
"image_path": "./data/IIIT5K/test/5041_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "swan",
|
|
"gt_answers": "SWAN",
|
|
"image_path": "./data/IIIT5K/test/5041_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "6",
|
|
"image_path": "./data/IIIT5K/test/5042_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "actress",
|
|
"gt_answers": "ACTRESS",
|
|
"image_path": "./data/IIIT5K/test/5042_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MERYL",
|
|
"image_path": "./data/IIIT5K/test/5042_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STREEP",
|
|
"image_path": "./data/IIIT5K/test/5042_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PICTURES",
|
|
"image_path": "./data/IIIT5K/test/5042_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/5042_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5042_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "doubt",
|
|
"gt_answers": "DOUBT",
|
|
"image_path": "./data/IIIT5K/test/5042_27.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/5042_28.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PLAYING",
|
|
"image_path": "./data/IIIT5K/test/5042_29.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nominations",
|
|
"gt_answers": "NOMINATIONS",
|
|
"image_path": "./data/IIIT5K/test/5042_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEST",
|
|
"image_path": "./data/IIIT5K/test/5042_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PICTURE",
|
|
"image_path": "./data/IIIT5K/test/5042_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "max",
|
|
"gt_answers": "MAX",
|
|
"image_path": "./data/IIIT5K/test/5043_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "payne",
|
|
"gt_answers": "PAYNE",
|
|
"image_path": "./data/IIIT5K/test/5043_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "george",
|
|
"gt_answers": "GEORGR",
|
|
"image_path": "./data/IIIT5K/test/5044_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRAD",
|
|
"image_path": "./data/IIIT5K/test/5044_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PITT",
|
|
"image_path": "./data/IIIT5K/test/5044_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BURN",
|
|
"image_path": "./data/IIIT5K/test/5044_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLOONEY",
|
|
"image_path": "./data/IIIT5K/test/5044_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FRANCES",
|
|
"image_path": "./data/IIIT5K/test/5044_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MCDORMAND",
|
|
"image_path": "./data/IIIT5K/test/5044_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JOHN",
|
|
"image_path": "./data/IIIT5K/test/5044_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MALKOVICH",
|
|
"image_path": "./data/IIIT5K/test/5044_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TILDA",
|
|
"image_path": "./data/IIIT5K/test/5044_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SWINTON",
|
|
"image_path": "./data/IIIT5K/test/5044_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/5044_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "of",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/5046_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "thunder",
|
|
"gt_answers": "THUNDER",
|
|
"image_path": "./data/IIIT5K/test/5046_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "thor",
|
|
"gt_answers": "THOR",
|
|
"image_path": "./data/IIIT5K/test/5046_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "may",
|
|
"gt_answers": "MAY",
|
|
"image_path": "./data/IIIT5K/test/5046_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "watchmen",
|
|
"gt_answers": "WATCHMEN",
|
|
"image_path": "./data/IIIT5K/test/5047_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALIENS",
|
|
"image_path": "./data/IIIT5K/test/5048_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5049_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "royal",
|
|
"gt_answers": "ROYAL",
|
|
"image_path": "./data/IIIT5K/test/5049_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tenenbaum",
|
|
"gt_answers": "TENENBAUMS",
|
|
"image_path": "./data/IIIT5K/test/5049_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEL",
|
|
"image_path": "./data/IIIT5K/test/5050_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WHEN",
|
|
"image_path": "./data/IIIT5K/test/5051_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WILL",
|
|
"image_path": "./data/IIIT5K/test/5051_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAWN",
|
|
"image_path": "./data/IIIT5K/test/5051_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5051_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEAD",
|
|
"image_path": "./data/IIIT5K/test/5051_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRST",
|
|
"image_path": "./data/IIIT5K/test/5051_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THERES",
|
|
"image_path": "./data/IIIT5K/test/5051_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAS",
|
|
"image_path": "./data/IIIT5K/test/5051_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIVING",
|
|
"image_path": "./data/IIIT5K/test/5051_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEAD",
|
|
"image_path": "./data/IIIT5K/test/5051_25.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/5051_26.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/5051_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5051_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEAD",
|
|
"image_path": "./data/IIIT5K/test/5051_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "iron",
|
|
"gt_answers": "IRON",
|
|
"image_path": "./data/IIIT5K/test/5052_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAN",
|
|
"image_path": "./data/IIIT5K/test/5052_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5053_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNITED",
|
|
"image_path": "./data/IIIT5K/test/5053_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATES",
|
|
"image_path": "./data/IIIT5K/test/5053_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STREET",
|
|
"image_path": "./data/IIIT5K/test/5054_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KINGS",
|
|
"image_path": "./data/IIIT5K/test/5054_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CITY",
|
|
"image_path": "./data/IIIT5K/test/5054_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THEIR",
|
|
"image_path": "./data/IIIT5K/test/5054_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RULES",
|
|
"image_path": "./data/IIIT5K/test/5054_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DATING",
|
|
"image_path": "./data/IIIT5K/test/5055_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BE",
|
|
"image_path": "./data/IIIT5K/test/5055_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MURDER",
|
|
"image_path": "./data/IIIT5K/test/5055_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MURDER",
|
|
"image_path": "./data/IIIT5K/test/5055_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VANTAGE",
|
|
"image_path": "./data/IIIT5K/test/5056_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3D",
|
|
"image_path": "./data/IIIT5K/test/5057_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEFY",
|
|
"image_path": "./data/IIIT5K/test/5059_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5059_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "future",
|
|
"gt_answers": "FUTURE",
|
|
"image_path": "./data/IIIT5K/test/5059_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "prince the sun",
|
|
"gt_answers": "PRINCE",
|
|
"image_path": "./data/IIIT5K/test/5059_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "persia",
|
|
"gt_answers": "PERSIA",
|
|
"image_path": "./data/IIIT5K/test/5059_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "die evil",
|
|
"gt_answers": "EVIL",
|
|
"image_path": "./data/IIIT5K/test/5061_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WHY",
|
|
"image_path": "./data/IIIT5K/test/5062_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SO",
|
|
"image_path": "./data/IIIT5K/test/5062_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SERIOUS",
|
|
"image_path": "./data/IIIT5K/test/5062_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5062_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DARK",
|
|
"image_path": "./data/IIIT5K/test/5062_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KNIGHT",
|
|
"image_path": "./data/IIIT5K/test/5062_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "anonymous",
|
|
"gt_answers": "ANONYMOUS",
|
|
"image_path": "./data/IIIT5K/test/5064_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POUR",
|
|
"image_path": "./data/IIIT5K/test/5065_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PREMIERE",
|
|
"image_path": "./data/IIIT5K/test/5065_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOIS",
|
|
"image_path": "./data/IIIT5K/test/5065_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LA",
|
|
"image_path": "./data/IIIT5K/test/5065_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jackass",
|
|
"gt_answers": "JACKASS",
|
|
"image_path": "./data/IIIT5K/test/5065_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3D",
|
|
"image_path": "./data/IIIT5K/test/5065_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AVERTISSEMENT",
|
|
"image_path": "./data/IIIT5K/test/5065_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DYLAN",
|
|
"image_path": "./data/IIIT5K/test/5067_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "dog",
|
|
"gt_answers": "DOG",
|
|
"image_path": "./data/IIIT5K/test/5067_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IL",
|
|
"image_path": "./data/IIIT5K/test/5067_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FILM",
|
|
"image_path": "./data/IIIT5K/test/5067_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAL",
|
|
"image_path": "./data/IIIT5K/test/5067_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOMEHOW",
|
|
"image_path": "./data/IIIT5K/test/5068_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "someone's blog",
|
|
"gt_answers": "SOMEONES",
|
|
"image_path": "./data/IIIT5K/test/5068_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOING",
|
|
"image_path": "./data/IIIT5K/test/5068_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JOAQUIN",
|
|
"image_path": "./data/IIIT5K/test/5069_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UTROLIGE",
|
|
"image_path": "./data/IIIT5K/test/5069_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "phoenix",
|
|
"gt_answers": "PHOENIX",
|
|
"image_path": "./data/IIIT5K/test/5069_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "person",
|
|
"gt_answers": "REESE",
|
|
"image_path": "./data/IIIT5K/test/5069_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "witherspoon",
|
|
"gt_answers": "WITHERSPOON",
|
|
"image_path": "./data/IIIT5K/test/5069_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "walk",
|
|
"gt_answers": "WALK",
|
|
"image_path": "./data/IIIT5K/test/5069_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5069_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LINE",
|
|
"image_path": "./data/IIIT5K/test/5069_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "johnny",
|
|
"gt_answers": "JOHNNY",
|
|
"image_path": "./data/IIIT5K/test/5070_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "deep",
|
|
"gt_answers": "DEEP",
|
|
"image_path": "./data/IIIT5K/test/5070_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/5070_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SWEENEY",
|
|
"image_path": "./data/IIIT5K/test/5070_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "todd",
|
|
"gt_answers": "TODD",
|
|
"image_path": "./data/IIIT5K/test/5070_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "christmas",
|
|
"gt_answers": "CHRISTMAS",
|
|
"image_path": "./data/IIIT5K/test/5070_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5071_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PARIS",
|
|
"image_path": "./data/IIIT5K/test/5073_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CATCH",
|
|
"image_path": "./data/IIIT5K/test/5073_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EVERETT",
|
|
"image_path": "./data/IIIT5K/test/5073_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SCOTT",
|
|
"image_path": "./data/IIIT5K/test/5073_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JULIE",
|
|
"image_path": "./data/IIIT5K/test/5073_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/5073_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jackie robinson",
|
|
"gt_answers": "JACKIE",
|
|
"image_path": "./data/IIIT5K/test/5074_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BROWN",
|
|
"image_path": "./data/IIIT5K/test/5074_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SO",
|
|
"image_path": "./data/IIIT5K/test/5075_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SERIOUS",
|
|
"image_path": "./data/IIIT5K/test/5075_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5075_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DARK",
|
|
"image_path": "./data/IIIT5K/test/5076_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KNIGHT",
|
|
"image_path": "./data/IIIT5K/test/5076_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "coming",
|
|
"gt_answers": "COMING",
|
|
"image_path": "./data/IIIT5K/test/5076_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOON",
|
|
"image_path": "./data/IIIT5K/test/5076_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "watchmen",
|
|
"gt_answers": "WATCHMEN",
|
|
"image_path": "./data/IIIT5K/test/5079_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/5079_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "300",
|
|
"image_path": "./data/IIIT5K/test/5079_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXPERIENCE",
|
|
"image_path": "./data/IIIT5K/test/5079_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IT",
|
|
"image_path": "./data/IIIT5K/test/5079_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/5079_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DIRECTOR",
|
|
"image_path": "./data/IIIT5K/test/5079_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/5080_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TAKE",
|
|
"image_path": "./data/IIIT5K/test/5080_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THEM",
|
|
"image_path": "./data/IIIT5K/test/5080_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jones",
|
|
"gt_answers": "JONES",
|
|
"image_path": "./data/IIIT5K/test/5080_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5080_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMPANY",
|
|
"image_path": "./data/IIIT5K/test/5080_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OUR",
|
|
"image_path": "./data/IIIT5K/test/5080_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIVES",
|
|
"image_path": "./data/IIIT5K/test/5080_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/5080_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "iron man",
|
|
"gt_answers": "IRON",
|
|
"image_path": "./data/IIIT5K/test/5081_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAN",
|
|
"image_path": "./data/IIIT5K/test/5081_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "iron man",
|
|
"gt_answers": "IRON",
|
|
"image_path": "./data/IIIT5K/test/5082_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAN",
|
|
"image_path": "./data/IIIT5K/test/5082_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOON",
|
|
"image_path": "./data/IIIT5K/test/5082_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TITANIC",
|
|
"image_path": "./data/IIIT5K/test/5083_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BALE",
|
|
"image_path": "./data/IIIT5K/test/5084_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BELL",
|
|
"image_path": "./data/IIIT5K/test/5084_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "freeman",
|
|
"gt_answers": "FREEMAN",
|
|
"image_path": "./data/IIIT5K/test/5084_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOTHAM",
|
|
"image_path": "./data/IIIT5K/test/5084_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPHULS",
|
|
"image_path": "./data/IIIT5K/test/5085_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "treblinka",
|
|
"gt_answers": "TREBLINKA",
|
|
"image_path": "./data/IIIT5K/test/5085_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/5085_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FILM",
|
|
"image_path": "./data/IIIT5K/test/5085_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BY",
|
|
"image_path": "./data/IIIT5K/test/5085_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREATEST",
|
|
"image_path": "./data/IIIT5K/test/5085_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOCUMENTARY",
|
|
"image_path": "./data/IIIT5K/test/5085_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ABOUT",
|
|
"image_path": "./data/IIIT5K/test/5085_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MARCEL",
|
|
"image_path": "./data/IIIT5K/test/5085_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NICK",
|
|
"image_path": "./data/IIIT5K/test/5086_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FROST",
|
|
"image_path": "./data/IIIT5K/test/5086_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "small town",
|
|
"gt_answers": "SMALL",
|
|
"image_path": "./data/IIIT5K/test/5086_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOWN",
|
|
"image_path": "./data/IIIT5K/test/5086_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MODERATE",
|
|
"image_path": "./data/IIIT5K/test/5086_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOT",
|
|
"image_path": "./data/IIIT5K/test/5086_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEING",
|
|
"image_path": "./data/IIIT5K/test/5088_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAMERON",
|
|
"image_path": "./data/IIIT5K/test/5088_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is diz",
|
|
"gt_answers": "DIAZ",
|
|
"image_path": "./data/IIIT5K/test/5088_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CATHERINE",
|
|
"image_path": "./data/IIIT5K/test/5088_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/5089_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRILLIANT",
|
|
"image_path": "./data/IIIT5K/test/5089_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOST",
|
|
"image_path": "./data/IIIT5K/test/5090_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ark",
|
|
"gt_answers": "ARK",
|
|
"image_path": "./data/IIIT5K/test/5090_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WHAT",
|
|
"image_path": "./data/IIIT5K/test/5091_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "it when you see it",
|
|
"gt_answers": "WHEN",
|
|
"image_path": "./data/IIIT5K/test/5091_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/5091_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DIE",
|
|
"image_path": "./data/IIIT5K/test/5091_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JURASSIC",
|
|
"image_path": "./data/IIIT5K/test/5092_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PARK",
|
|
"image_path": "./data/IIIT5K/test/5092_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOVIEGOODS",
|
|
"image_path": "./data/IIIT5K/test/5092_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/5092_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AVATAR",
|
|
"image_path": "./data/IIIT5K/test/5093_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AJITH",
|
|
"image_path": "./data/IIIT5K/test/5094_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NAG",
|
|
"image_path": "./data/IIIT5K/test/5094_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MANGATHA",
|
|
"image_path": "./data/IIIT5K/test/5094_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DARK",
|
|
"image_path": "./data/IIIT5K/test/5095_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "18",
|
|
"gt_answers": "18",
|
|
"image_path": "./data/IIIT5K/test/5095_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "love",
|
|
"gt_answers": "LOVE",
|
|
"image_path": "./data/IIIT5K/test/5096_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/5096_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALEX",
|
|
"image_path": "./data/IIIT5K/test/5096_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pettyfer",
|
|
"gt_answers": "PETTYFER",
|
|
"image_path": "./data/IIIT5K/test/5096_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "easily",
|
|
"gt_answers": "EASTLY",
|
|
"image_path": "./data/IIIT5K/test/5096_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOON",
|
|
"image_path": "./data/IIIT5K/test/5098_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "saw",
|
|
"gt_answers": "SAW",
|
|
"image_path": "./data/IIIT5K/test/5099_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IV",
|
|
"image_path": "./data/IIIT5K/test/5099_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": ": restaurant",
|
|
"gt_answers": "RESTAURANT",
|
|
"image_path": "./data/IIIT5K/test/509_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IRISH",
|
|
"image_path": "./data/IIIT5K/test/509_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SPIDER",
|
|
"image_path": "./data/IIIT5K/test/5100_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAN",
|
|
"image_path": "./data/IIIT5K/test/5100_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOLARIS",
|
|
"image_path": "./data/IIIT5K/test/5101_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POJEDYNEK",
|
|
"image_path": "./data/IIIT5K/test/5102_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POTWOROW",
|
|
"image_path": "./data/IIIT5K/test/5102_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAR",
|
|
"image_path": "./data/IIIT5K/test/5103_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "1984",
|
|
"gt_answers": "1984",
|
|
"image_path": "./data/IIIT5K/test/5103_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HURT",
|
|
"image_path": "./data/IIIT5K/test/5103_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROSSELLINI",
|
|
"image_path": "./data/IIIT5K/test/5103_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RONALD",
|
|
"image_path": "./data/IIIT5K/test/5103_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REAGAN",
|
|
"image_path": "./data/IIIT5K/test/5103_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BIG",
|
|
"image_path": "./data/IIIT5K/test/5103_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BROTHER",
|
|
"image_path": "./data/IIIT5K/test/5103_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ORION",
|
|
"image_path": "./data/IIIT5K/test/5103_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SLAVERY",
|
|
"image_path": "./data/IIIT5K/test/5103_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IGNORANCE",
|
|
"image_path": "./data/IIIT5K/test/5103_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/5103_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/5104_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "colored",
|
|
"gt_answers": "COLURED",
|
|
"image_path": "./data/IIIT5K/test/5104_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5107_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THEM",
|
|
"image_path": "./data/IIIT5K/test/5107_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEMORIAL",
|
|
"image_path": "./data/IIIT5K/test/5107_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAY",
|
|
"image_path": "./data/IIIT5K/test/5107_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wolfpack",
|
|
"gt_answers": "WOLFPACK",
|
|
"image_path": "./data/IIIT5K/test/5107_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/5107_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANGKOK",
|
|
"image_path": "./data/IIIT5K/test/5107_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAS",
|
|
"image_path": "./data/IIIT5K/test/5107_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TELETECH",
|
|
"image_path": "./data/IIIT5K/test/510_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twilight",
|
|
"gt_answers": "TWILIGHT",
|
|
"image_path": "./data/IIIT5K/test/5110_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "indiana jones",
|
|
"gt_answers": "JONES",
|
|
"image_path": "./data/IIIT5K/test/5114_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CRYSTAL",
|
|
"image_path": "./data/IIIT5K/test/5114_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SKULL",
|
|
"image_path": "./data/IIIT5K/test/5114_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAY",
|
|
"image_path": "./data/IIIT5K/test/5114_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twilight",
|
|
"gt_answers": "TWILIGHT",
|
|
"image_path": "./data/IIIT5K/test/5115_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "statham",
|
|
"gt_answers": "STATHAM",
|
|
"image_path": "./data/IIIT5K/test/5116_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ben",
|
|
"gt_answers": "BEN",
|
|
"image_path": "./data/IIIT5K/test/5116_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "foster",
|
|
"gt_answers": "FOSTER",
|
|
"image_path": "./data/IIIT5K/test/5116_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twilight",
|
|
"gt_answers": "TWILIGHT",
|
|
"image_path": "./data/IIIT5K/test/5118_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "new",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/5118_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "112009",
|
|
"image_path": "./data/IIIT5K/test/5118_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twilight",
|
|
"gt_answers": "TWILIGHT",
|
|
"image_path": "./data/IIIT5K/test/5119_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "new",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/5119_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOON",
|
|
"image_path": "./data/IIIT5K/test/5119_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOLVE",
|
|
"image_path": "./data/IIIT5K/test/511_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "life",
|
|
"gt_answers": "LIFE",
|
|
"image_path": "./data/IIIT5K/test/511_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SMS",
|
|
"image_path": "./data/IIIT5K/test/511_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sbi logo",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/511_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TIME",
|
|
"image_path": "./data/IIIT5K/test/5129_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "prince",
|
|
"gt_answers": "PRINCE",
|
|
"image_path": "./data/IIIT5K/test/5129_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/5129_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "persia",
|
|
"gt_answers": "PERSIA",
|
|
"image_path": "./data/IIIT5K/test/5129_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5129_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RICK",
|
|
"image_path": "./data/IIIT5K/test/5130_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAVIDSON",
|
|
"image_path": "./data/IIIT5K/test/5130_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "march",
|
|
"gt_answers": "MARCH",
|
|
"image_path": "./data/IIIT5K/test/5130_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "08",
|
|
"image_path": "./data/IIIT5K/test/5130_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ORIGINAL",
|
|
"image_path": "./data/IIIT5K/test/5131_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SYLVESTER",
|
|
"image_path": "./data/IIIT5K/test/5131_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5132_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ULTIMATE",
|
|
"image_path": "./data/IIIT5K/test/5132_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MAN",
|
|
"image_path": "./data/IIIT5K/test/5132_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/5132_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EARTH",
|
|
"image_path": "./data/IIIT5K/test/5132_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SPOTTING",
|
|
"image_path": "./data/IIIT5K/test/5133_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SICK",
|
|
"image_path": "./data/IIIT5K/test/5133_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOY",
|
|
"image_path": "./data/IIIT5K/test/5133_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tiffany",
|
|
"gt_answers": "TIFFANY",
|
|
"image_path": "./data/IIIT5K/test/5134_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WYSTEPUJA",
|
|
"image_path": "./data/IIIT5K/test/5134_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AUDREY",
|
|
"image_path": "./data/IIIT5K/test/5134_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HEPBURN",
|
|
"image_path": "./data/IIIT5K/test/5134_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "roza",
|
|
"gt_answers": "ROZRA",
|
|
"image_path": "./data/IIIT5K/test/5135_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AJA",
|
|
"image_path": "./data/IIIT5K/test/5135_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POWROT",
|
|
"image_path": "./data/IIIT5K/test/5136_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/5137_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOUSE",
|
|
"image_path": "./data/IIIT5K/test/5137_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "why",
|
|
"gt_answers": "WHY",
|
|
"image_path": "./data/IIIT5K/test/5137_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHANGELING",
|
|
"image_path": "./data/IIIT5K/test/5137_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/5137_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DIE",
|
|
"image_path": "./data/IIIT5K/test/5137_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "joseph",
|
|
"gt_answers": "JOSEPH",
|
|
"image_path": "./data/IIIT5K/test/5137_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5138_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "depth",
|
|
"gt_answers": "DEPTHS",
|
|
"image_path": "./data/IIIT5K/test/5138_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VACATION",
|
|
"image_path": "./data/IIIT5K/test/5138_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/5138_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FROM",
|
|
"image_path": "./data/IIIT5K/test/5138_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twilight",
|
|
"gt_answers": "TWILIGHT",
|
|
"image_path": "./data/IIIT5K/test/5139_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "boxing",
|
|
"gt_answers": "BOXING",
|
|
"image_path": "./data/IIIT5K/test/5141_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "rescue",
|
|
"gt_answers": "RESCUE",
|
|
"image_path": "./data/IIIT5K/test/5142_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "dennis",
|
|
"gt_answers": "DENNIS",
|
|
"image_path": "./data/IIIT5K/test/5143_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hopper's",
|
|
"gt_answers": "HOPPERS",
|
|
"image_path": "./data/IIIT5K/test/5143_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pop",
|
|
"gt_answers": "POP",
|
|
"image_path": "./data/IIIT5K/test/5143_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "full",
|
|
"gt_answers": "FULL",
|
|
"image_path": "./data/IIIT5K/test/5144_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "metal",
|
|
"gt_answers": "METAL",
|
|
"image_path": "./data/IIIT5K/test/5144_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jacket",
|
|
"gt_answers": "JACKET",
|
|
"image_path": "./data/IIIT5K/test/5144_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "veer",
|
|
"gt_answers": "VEER",
|
|
"image_path": "./data/IIIT5K/test/5145_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "right",
|
|
"gt_answers": "RIGHT",
|
|
"image_path": "./data/IIIT5K/test/5146_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WRONG",
|
|
"image_path": "./data/IIIT5K/test/5146_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DISNEY",
|
|
"image_path": "./data/IIIT5K/test/5147_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tron",
|
|
"gt_answers": "TRON",
|
|
"image_path": "./data/IIIT5K/test/5147_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LEGACY",
|
|
"image_path": "./data/IIIT5K/test/5147_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/5147_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KARLOFF",
|
|
"image_path": "./data/IIIT5K/test/5148_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AMANDA",
|
|
"image_path": "./data/IIIT5K/test/5148_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SEYFRIED",
|
|
"image_path": "./data/IIIT5K/test/5148_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "frank",
|
|
"gt_answers": "FRANK",
|
|
"image_path": "./data/IIIT5K/test/5148_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEPOSIT",
|
|
"image_path": "./data/IIIT5K/test/514_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PHOTOS",
|
|
"image_path": "./data/IIIT5K/test/514_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EAGLE",
|
|
"image_path": "./data/IIIT5K/test/5150_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "eye",
|
|
"gt_answers": "EYE",
|
|
"image_path": "./data/IIIT5K/test/5150_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cinema masterpieces",
|
|
"gt_answers": "CINEMASTERPIECES",
|
|
"image_path": "./data/IIIT5K/test/5151_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PITT",
|
|
"image_path": "./data/IIIT5K/test/5152_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "megamind",
|
|
"gt_answers": "MEGAMIND",
|
|
"image_path": "./data/IIIT5K/test/5152_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "3d",
|
|
"gt_answers": "3D",
|
|
"image_path": "./data/IIIT5K/test/5152_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "denzel",
|
|
"gt_answers": "DENZEL",
|
|
"image_path": "./data/IIIT5K/test/5153_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WASHINGTON",
|
|
"image_path": "./data/IIIT5K/test/5153_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "unstoppable",
|
|
"gt_answers": "UNSTOPPABLE",
|
|
"image_path": "./data/IIIT5K/test/5153_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5154_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEFORE",
|
|
"image_path": "./data/IIIT5K/test/5154_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GIJOE",
|
|
"image_path": "./data/IIIT5K/test/5162_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "august",
|
|
"gt_answers": "AUGUST",
|
|
"image_path": "./data/IIIT5K/test/5162_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "7",
|
|
"image_path": "./data/IIIT5K/test/5162_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5163_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PENA",
|
|
"image_path": "./data/IIIT5K/test/5165_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "observe",
|
|
"gt_answers": "OBSERVE",
|
|
"image_path": "./data/IIIT5K/test/5165_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REPORT",
|
|
"image_path": "./data/IIIT5K/test/5165_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORLD",
|
|
"image_path": "./data/IIIT5K/test/5165_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "all needs",
|
|
"gt_answers": "NEEDS",
|
|
"image_path": "./data/IIIT5K/test/5165_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/5165_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "person",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5167_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the question",
|
|
"gt_answers": "SOLOIST",
|
|
"image_path": "./data/IIIT5K/test/5167_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HARRY",
|
|
"image_path": "./data/IIIT5K/test/5169_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5169_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/5170_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FEW",
|
|
"image_path": "./data/IIIT5K/test/5170_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOLLARS",
|
|
"image_path": "./data/IIIT5K/test/5170_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MORE",
|
|
"image_path": "./data/IIIT5K/test/5170_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HIS",
|
|
"image_path": "./data/IIIT5K/test/5171_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADVENTURE",
|
|
"image_path": "./data/IIIT5K/test/5171_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/5171_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "leisure",
|
|
"gt_answers": "LEISURE",
|
|
"image_path": "./data/IIIT5K/test/5172_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RULES",
|
|
"image_path": "./data/IIIT5K/test/5172_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OFF",
|
|
"image_path": "./data/IIIT5K/test/5172_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THEY",
|
|
"image_path": "./data/IIIT5K/test/5173_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIVE",
|
|
"image_path": "./data/IIIT5K/test/5173_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "APOLLO",
|
|
"image_path": "./data/IIIT5K/test/5174_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "13",
|
|
"gt_answers": "13",
|
|
"image_path": "./data/IIIT5K/test/5174_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/5176_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "after",
|
|
"gt_answers": "AFTER",
|
|
"image_path": "./data/IIIT5K/test/5176_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KINGS",
|
|
"image_path": "./data/IIIT5K/test/5177_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHANGES",
|
|
"image_path": "./data/IIIT5K/test/517_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ANGELINA",
|
|
"image_path": "./data/IIIT5K/test/5181_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JOLIE",
|
|
"image_path": "./data/IIIT5K/test/5181_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "salt",
|
|
"gt_answers": "SALT",
|
|
"image_path": "./data/IIIT5K/test/5181_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2010",
|
|
"image_path": "./data/IIIT5K/test/5181_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pulp",
|
|
"gt_answers": "PULP",
|
|
"image_path": "./data/IIIT5K/test/5182_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FICTION",
|
|
"image_path": "./data/IIIT5K/test/5182_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tango",
|
|
"gt_answers": "TANGO",
|
|
"image_path": "./data/IIIT5K/test/5183_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the cash",
|
|
"gt_answers": "CASH",
|
|
"image_path": "./data/IIIT5K/test/5183_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5184_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORLD",
|
|
"image_path": "./data/IIIT5K/test/5184_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ghostbusters",
|
|
"gt_answers": "GHOSTBUSTERS",
|
|
"image_path": "./data/IIIT5K/test/5184_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/5186_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "film",
|
|
"gt_answers": "FILM",
|
|
"image_path": "./data/IIIT5K/test/5186_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BY",
|
|
"image_path": "./data/IIIT5K/test/5186_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/5187_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "door",
|
|
"gt_answers": "DOOR",
|
|
"image_path": "./data/IIIT5K/test/5187_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the spirit",
|
|
"gt_answers": "SPIRIT",
|
|
"image_path": "./data/IIIT5K/test/5188_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOGART",
|
|
"image_path": "./data/IIIT5K/test/5189_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HENREID",
|
|
"image_path": "./data/IIIT5K/test/5189_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WILD",
|
|
"image_path": "./data/IIIT5K/test/5191_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "winner",
|
|
"gt_answers": "WINNER",
|
|
"image_path": "./data/IIIT5K/test/5192_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LEONARDO",
|
|
"image_path": "./data/IIIT5K/test/5192_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HALLOWEEN",
|
|
"image_path": "./data/IIIT5K/test/5193_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FROST",
|
|
"image_path": "./data/IIIT5K/test/5194_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NIXON",
|
|
"image_path": "./data/IIIT5K/test/5194_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "manhattan",
|
|
"gt_answers": "MANHATTAN",
|
|
"image_path": "./data/IIIT5K/test/5195_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "breakfast delights",
|
|
"gt_answers": "BREAKFAST",
|
|
"image_path": "./data/IIIT5K/test/5196_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TIFFANYS",
|
|
"image_path": "./data/IIIT5K/test/5196_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "simon",
|
|
"gt_answers": "SIMON",
|
|
"image_path": "./data/IIIT5K/test/5197_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "says",
|
|
"gt_answers": "SAYS",
|
|
"image_path": "./data/IIIT5K/test/5197_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "soon",
|
|
"gt_answers": "SOON",
|
|
"image_path": "./data/IIIT5K/test/5197_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "paul",
|
|
"gt_answers": "PAUL",
|
|
"image_path": "./data/IIIT5K/test/5198_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOOD",
|
|
"image_path": "./data/IIIT5K/test/5199_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TERMINAL",
|
|
"image_path": "./data/IIIT5K/test/51_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "superman",
|
|
"gt_answers": "SUPERMAN",
|
|
"image_path": "./data/IIIT5K/test/5200_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5200_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CARS",
|
|
"image_path": "./data/IIIT5K/test/5201_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "priest",
|
|
"gt_answers": "PRIEST",
|
|
"image_path": "./data/IIIT5K/test/5202_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "guerra",
|
|
"gt_answers": "GUERRA",
|
|
"image_path": "./data/IIIT5K/test/5202_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SERA",
|
|
"image_path": "./data/IIIT5K/test/5202_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "eternal",
|
|
"gt_answers": "ETERNA",
|
|
"image_path": "./data/IIIT5K/test/5202_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "paladin",
|
|
"gt_answers": "PALADIN",
|
|
"image_path": "./data/IIIT5K/test/5203_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PROPOSITION",
|
|
"image_path": "./data/IIIT5K/test/5208_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TERRY",
|
|
"image_path": "./data/IIIT5K/test/5209_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GILLIAM",
|
|
"image_path": "./data/IIIT5K/test/5209_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TIDE",
|
|
"image_path": "./data/IIIT5K/test/5209_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "heroes",
|
|
"gt_answers": "HEROES",
|
|
"image_path": "./data/IIIT5K/test/520_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIKE",
|
|
"image_path": "./data/IIIT5K/test/520_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOGART",
|
|
"image_path": "./data/IIIT5K/test/520_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SKY",
|
|
"image_path": "./data/IIIT5K/test/520_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the giant",
|
|
"gt_answers": "GIANT",
|
|
"image_path": "./data/IIIT5K/test/5212_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "leeches",
|
|
"gt_answers": "LEECHES",
|
|
"image_path": "./data/IIIT5K/test/5212_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ME",
|
|
"image_path": "./data/IIIT5K/test/5214_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/5214_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DABBE",
|
|
"image_path": "./data/IIIT5K/test/5215_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is in the title",
|
|
"gt_answers": "NIN",
|
|
"image_path": "./data/IIIT5K/test/5215_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the title of the song",
|
|
"gt_answers": "YONETMENINDEN",
|
|
"image_path": "./data/IIIT5K/test/5215_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "terminator",
|
|
"gt_answers": "TERMINATOR",
|
|
"image_path": "./data/IIIT5K/test/5216_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the gods need a hero immortals",
|
|
"gt_answers": "IMMORTALS",
|
|
"image_path": "./data/IIIT5K/test/5217_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "district",
|
|
"gt_answers": "DISTRICT",
|
|
"image_path": "./data/IIIT5K/test/5220_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10",
|
|
"image_path": "./data/IIIT5K/test/5220_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SCARS",
|
|
"image_path": "./data/IIIT5K/test/5221_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the road",
|
|
"gt_answers": "ROAD",
|
|
"image_path": "./data/IIIT5K/test/5224_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "eragon",
|
|
"gt_answers": "ERAGON",
|
|
"image_path": "./data/IIIT5K/test/5225_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "duke",
|
|
"gt_answers": "DUKE",
|
|
"image_path": "./data/IIIT5K/test/5227_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/5228_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/5228_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MATT",
|
|
"image_path": "./data/IIIT5K/test/5228_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAMON",
|
|
"image_path": "./data/IIIT5K/test/5228_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/522_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/522_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/522_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/522_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/522_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/522_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/526_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/528_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/528_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/528_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "clear",
|
|
"gt_answers": "CLEAR",
|
|
"image_path": "./data/IIIT5K/test/529_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "oct t",
|
|
"gt_answers": "OCT",
|
|
"image_path": "./data/IIIT5K/test/529_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "24",
|
|
"gt_answers": "24",
|
|
"image_path": "./data/IIIT5K/test/529_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "st",
|
|
"gt_answers": "ST",
|
|
"image_path": "./data/IIIT5K/test/529_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "asun",
|
|
"gt_answers": "ASUN",
|
|
"image_path": "./data/IIIT5K/test/529_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is unr",
|
|
"gt_answers": "UNR",
|
|
"image_path": "./data/IIIT5K/test/529_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "channel",
|
|
"gt_answers": "CHANNEL",
|
|
"image_path": "./data/IIIT5K/test/529_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pack",
|
|
"gt_answers": "PACK",
|
|
"image_path": "./data/IIIT5K/test/529_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pack",
|
|
"gt_answers": "PACK",
|
|
"image_path": "./data/IIIT5K/test/529_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "our",
|
|
"gt_answers": "OUR",
|
|
"image_path": "./data/IIIT5K/test/529_25.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PACK",
|
|
"image_path": "./data/IIIT5K/test/529_26.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wolf",
|
|
"gt_answers": "WOLF",
|
|
"image_path": "./data/IIIT5K/test/529_27.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "university",
|
|
"gt_answers": "UNIVERSITY",
|
|
"image_path": "./data/IIIT5K/test/529_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is off",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/529_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nevada",
|
|
"gt_answers": "NEVADA",
|
|
"image_path": "./data/IIIT5K/test/529_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sat",
|
|
"gt_answers": "SAT",
|
|
"image_path": "./data/IIIT5K/test/529_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "24",
|
|
"image_path": "./data/IIIT5K/test/52_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOURS",
|
|
"image_path": "./data/IIIT5K/test/52_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "atm",
|
|
"gt_answers": "ATM",
|
|
"image_path": "./data/IIIT5K/test/52_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/530_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BACK",
|
|
"image_path": "./data/IIIT5K/test/530_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEHANIKA",
|
|
"image_path": "./data/IIIT5K/test/532_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "I",
|
|
"image_path": "./data/IIIT5K/test/532_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DIJAGNOSTIKA",
|
|
"image_path": "./data/IIIT5K/test/532_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRODAJA",
|
|
"image_path": "./data/IIIT5K/test/532_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VOZILA",
|
|
"image_path": "./data/IIIT5K/test/532_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PRODAJA",
|
|
"image_path": "./data/IIIT5K/test/532_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hollywood",
|
|
"gt_answers": "HOLLYWOOD",
|
|
"image_path": "./data/IIIT5K/test/535_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "all stars",
|
|
"gt_answers": "ALLSTARS",
|
|
"image_path": "./data/IIIT5K/test/535_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/535_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertising",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/535_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOLUTION",
|
|
"image_path": "./data/IIIT5K/test/535_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RELIANCE",
|
|
"image_path": "./data/IIIT5K/test/538_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/541_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/541_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/545_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/545_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "atm",
|
|
"gt_answers": "ATM",
|
|
"image_path": "./data/IIIT5K/test/545_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/546_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUSINESS",
|
|
"image_path": "./data/IIIT5K/test/546_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CALL",
|
|
"image_path": "./data/IIIT5K/test/546_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "919",
|
|
"image_path": "./data/IIIT5K/test/546_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "5218249",
|
|
"image_path": "./data/IIIT5K/test/546_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "emergency",
|
|
"gt_answers": "EMERGENCY",
|
|
"image_path": "./data/IIIT5K/test/548_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/548_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DESIGNSTOCKZ",
|
|
"image_path": "./data/IIIT5K/test/548_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOLLOW",
|
|
"image_path": "./data/IIIT5K/test/549_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "ashton",
|
|
"gt_answers": "ASHTON",
|
|
"image_path": "./data/IIIT5K/test/549_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KUTCHER",
|
|
"image_path": "./data/IIIT5K/test/549_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twitter",
|
|
"gt_answers": "TWITTER",
|
|
"image_path": "./data/IIIT5K/test/549_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/551_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/551_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/551_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "neon sign",
|
|
"gt_answers": "LIMITED",
|
|
"image_path": "./data/IIIT5K/test/554_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALE",
|
|
"image_path": "./data/IIIT5K/test/554_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MSN",
|
|
"image_path": "./data/IIIT5K/test/555_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOR",
|
|
"image_path": "./data/IIIT5K/test/570_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOFU",
|
|
"image_path": "./data/IIIT5K/test/570_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "share",
|
|
"gt_answers": "SHARE",
|
|
"image_path": "./data/IIIT5K/test/574_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "delete",
|
|
"gt_answers": "DELETE",
|
|
"image_path": "./data/IIIT5K/test/575_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/584_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SCHEDULE",
|
|
"image_path": "./data/IIIT5K/test/584_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HITS",
|
|
"image_path": "./data/IIIT5K/test/584_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STREETS",
|
|
"image_path": "./data/IIIT5K/test/584_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sept 2",
|
|
"gt_answers": "SEPT2",
|
|
"image_path": "./data/IIIT5K/test/584_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AHEAD",
|
|
"image_path": "./data/IIIT5K/test/585_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORK",
|
|
"image_path": "./data/IIIT5K/test/585_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZONE",
|
|
"image_path": "./data/IIIT5K/test/585_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EAT",
|
|
"image_path": "./data/IIIT5K/test/586_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REST",
|
|
"image_path": "./data/IIIT5K/test/586_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STOP",
|
|
"image_path": "./data/IIIT5K/test/586_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "50TH",
|
|
"image_path": "./data/IIIT5K/test/587_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NESTLE",
|
|
"image_path": "./data/IIIT5K/test/589_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/590_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DE",
|
|
"image_path": "./data/IIIT5K/test/590_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SPOTLIGHT",
|
|
"image_path": "./data/IIIT5K/test/590_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OOK",
|
|
"image_path": "./data/IIIT5K/test/590_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/590_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DE",
|
|
"image_path": "./data/IIIT5K/test/590_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DE",
|
|
"image_path": "./data/IIIT5K/test/590_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SPOTLIGHT",
|
|
"image_path": "./data/IIIT5K/test/590_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "stan",
|
|
"gt_answers": "STAAN",
|
|
"image_path": "./data/IIIT5K/test/590_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/591_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/591_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/591_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COFFEE",
|
|
"image_path": "./data/IIIT5K/test/592_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOARD",
|
|
"image_path": "./data/IIIT5K/test/593_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "right",
|
|
"gt_answers": "RIGHT",
|
|
"image_path": "./data/IIIT5K/test/594_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "on",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/594_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "9365978448",
|
|
"image_path": "./data/IIIT5K/test/594_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COUPON",
|
|
"image_path": "./data/IIIT5K/test/595_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CODE",
|
|
"image_path": "./data/IIIT5K/test/595_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "only pay 1 cent",
|
|
"gt_answers": "ONLYPAY1CENT",
|
|
"image_path": "./data/IIIT5K/test/595_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WEBSITE",
|
|
"image_path": "./data/IIIT5K/test/595_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TODAY",
|
|
"image_path": "./data/IIIT5K/test/595_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOST",
|
|
"image_path": "./data/IIIT5K/test/595_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEWSPAPERS",
|
|
"image_path": "./data/IIIT5K/test/596_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1000",
|
|
"image_path": "./data/IIIT5K/test/596_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIEWERS",
|
|
"image_path": "./data/IIIT5K/test/596_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIFES",
|
|
"image_path": "./data/IIIT5K/test/597_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3123410900",
|
|
"image_path": "./data/IIIT5K/test/597_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SEE",
|
|
"image_path": "./data/IIIT5K/test/598_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRUNOS",
|
|
"image_path": "./data/IIIT5K/test/598_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "830",
|
|
"image_path": "./data/IIIT5K/test/598_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AM",
|
|
"image_path": "./data/IIIT5K/test/598_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FGALAWFIRM",
|
|
"image_path": "./data/IIIT5K/test/599_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/599_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "divorce",
|
|
"gt_answers": "DIVORCE",
|
|
"image_path": "./data/IIIT5K/test/599_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3123410900",
|
|
"image_path": "./data/IIIT5K/test/599_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SREELAKSHMI",
|
|
"image_path": "./data/IIIT5K/test/59_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REYAMI",
|
|
"image_path": "./data/IIIT5K/test/59_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GET",
|
|
"image_path": "./data/IIIT5K/test/600_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/600_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "divorce",
|
|
"gt_answers": "DIVORCE",
|
|
"image_path": "./data/IIIT5K/test/600_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GET",
|
|
"image_path": "./data/IIIT5K/test/601_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/601_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "divorce",
|
|
"gt_answers": "DIVORCE",
|
|
"image_path": "./data/IIIT5K/test/601_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KWIK",
|
|
"image_path": "./data/IIIT5K/test/603_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/603_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUYER",
|
|
"image_path": "./data/IIIT5K/test/603_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "houses",
|
|
"gt_answers": "HOUSES",
|
|
"image_path": "./data/IIIT5K/test/603_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ANY",
|
|
"image_path": "./data/IIIT5K/test/603_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CONDITION",
|
|
"image_path": "./data/IIIT5K/test/603_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KDFW",
|
|
"image_path": "./data/IIIT5K/test/605_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEBENHAMS",
|
|
"image_path": "./data/IIIT5K/test/606_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OFF",
|
|
"image_path": "./data/IIIT5K/test/606_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LILLIPUT",
|
|
"image_path": "./data/IIIT5K/test/60_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "3",
|
|
"image_path": "./data/IIIT5K/test/610_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "friends",
|
|
"gt_answers": "FRIENDS",
|
|
"image_path": "./data/IIIT5K/test/610_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOST",
|
|
"image_path": "./data/IIIT5K/test/610_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEWS",
|
|
"image_path": "./data/IIIT5K/test/612_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRST",
|
|
"image_path": "./data/IIIT5K/test/616_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "10 digit",
|
|
"gt_answers": "10DIGIT",
|
|
"image_path": "./data/IIIT5K/test/616_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "digits",
|
|
"gt_answers": "DIGITS",
|
|
"image_path": "./data/IIIT5K/test/616_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/616_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "E",
|
|
"image_path": "./data/IIIT5K/test/616_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARDS",
|
|
"image_path": "./data/IIIT5K/test/620_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FROM",
|
|
"image_path": "./data/IIIT5K/test/620_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLY",
|
|
"image_path": "./data/IIIT5K/test/620_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RECEIVING",
|
|
"image_path": "./data/IIIT5K/test/622_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOVO",
|
|
"image_path": "./data/IIIT5K/test/626_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "nordisk",
|
|
"gt_answers": "NORDISK",
|
|
"image_path": "./data/IIIT5K/test/626_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "staples",
|
|
"gt_answers": "STAPLES",
|
|
"image_path": "./data/IIIT5K/test/629_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CENTER",
|
|
"image_path": "./data/IIIT5K/test/629_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEANS",
|
|
"image_path": "./data/IIIT5K/test/629_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "50",
|
|
"image_path": "./data/IIIT5K/test/629_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "open",
|
|
"gt_answers": "OPEN",
|
|
"image_path": "./data/IIIT5K/test/62_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/62_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HIRING",
|
|
"image_path": "./data/IIIT5K/test/62_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "no 1",
|
|
"gt_answers": "NO1",
|
|
"image_path": "./data/IIIT5K/test/62_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "govt",
|
|
"gt_answers": "GOVT",
|
|
"image_path": "./data/IIIT5K/test/62_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JOB",
|
|
"image_path": "./data/IIIT5K/test/62_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "site",
|
|
"gt_answers": "SITE",
|
|
"image_path": "./data/IIIT5K/test/62_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SERVICE",
|
|
"image_path": "./data/IIIT5K/test/632_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDONESIA",
|
|
"image_path": "./data/IIIT5K/test/632_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "comap",
|
|
"gt_answers": "COMAP",
|
|
"image_path": "./data/IIIT5K/test/632_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/633_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MORE",
|
|
"image_path": "./data/IIIT5K/test/633_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ANSON",
|
|
"image_path": "./data/IIIT5K/test/634_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NIKON",
|
|
"image_path": "./data/IIIT5K/test/638_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/639_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tv",
|
|
"gt_answers": "TV",
|
|
"image_path": "./data/IIIT5K/test/639_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/63_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/63_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "in the comments",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/63_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "india",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/63_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/641_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/644_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HYDERABAD",
|
|
"image_path": "./data/IIIT5K/test/644_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/64_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/64_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/64_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jedah",
|
|
"gt_answers": "JEDDAH",
|
|
"image_path": "./data/IIIT5K/test/64_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PHOTO",
|
|
"image_path": "./data/IIIT5K/test/64_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JEDDAHPHOTOBLOGSPOTCOM",
|
|
"image_path": "./data/IIIT5K/test/64_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "60",
|
|
"image_path": "./data/IIIT5K/test/650_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mummies",
|
|
"gt_answers": "MUMMIES",
|
|
"image_path": "./data/IIIT5K/test/653_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GET",
|
|
"image_path": "./data/IIIT5K/test/655_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HER",
|
|
"image_path": "./data/IIIT5K/test/655_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/655_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOM",
|
|
"image_path": "./data/IIIT5K/test/65_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HANKS",
|
|
"image_path": "./data/IIIT5K/test/65_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "angels",
|
|
"gt_answers": "ANGELS",
|
|
"image_path": "./data/IIIT5K/test/65_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEMONS",
|
|
"image_path": "./data/IIIT5K/test/65_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VAN",
|
|
"image_path": "./data/IIIT5K/test/65_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BE",
|
|
"image_path": "./data/IIIT5K/test/664_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "enlightened",
|
|
"gt_answers": "ENLIGHTENED",
|
|
"image_path": "./data/IIIT5K/test/664_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BE",
|
|
"image_path": "./data/IIIT5K/test/665_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ENLIGHTENED",
|
|
"image_path": "./data/IIIT5K/test/665_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WERE",
|
|
"image_path": "./data/IIIT5K/test/666_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "all",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/666_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "over",
|
|
"gt_answers": "OVER",
|
|
"image_path": "./data/IIIT5K/test/666_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOWN",
|
|
"image_path": "./data/IIIT5K/test/666_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "outdoor",
|
|
"gt_answers": "OUTDOOR",
|
|
"image_path": "./data/IIIT5K/test/666_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AIRLINES",
|
|
"image_path": "./data/IIIT5K/test/667_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KLEIN",
|
|
"image_path": "./data/IIIT5K/test/66_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state department",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/671_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "it is a sign",
|
|
"gt_answers": "OVERSEAS",
|
|
"image_path": "./data/IIIT5K/test/671_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/672_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "message",
|
|
"gt_answers": "MESSAGE",
|
|
"image_path": "./data/IIIT5K/test/672_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HERE",
|
|
"image_path": "./data/IIIT5K/test/672_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOOK",
|
|
"image_path": "./data/IIIT5K/test/672_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOW",
|
|
"image_path": "./data/IIIT5K/test/672_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "crawford",
|
|
"gt_answers": "CRAWFORD",
|
|
"image_path": "./data/IIIT5K/test/673_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZALAD",
|
|
"image_path": "./data/IIIT5K/test/673_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "right",
|
|
"gt_answers": "RIGHT",
|
|
"image_path": "./data/IIIT5K/test/673_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/673_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "14TH",
|
|
"image_path": "./data/IIIT5K/test/673_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ST",
|
|
"image_path": "./data/IIIT5K/test/673_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZAXBYS",
|
|
"image_path": "./data/IIIT5K/test/673_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JEWELERS",
|
|
"image_path": "./data/IIIT5K/test/673_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOVE",
|
|
"image_path": "./data/IIIT5K/test/673_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "inspired",
|
|
"gt_answers": "INSPIRED",
|
|
"image_path": "./data/IIIT5K/test/673_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "can",
|
|
"gt_answers": "CAN",
|
|
"image_path": "./data/IIIT5K/test/673_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "will",
|
|
"gt_answers": "WILL",
|
|
"image_path": "./data/IIIT5K/test/67_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "be",
|
|
"gt_answers": "BE",
|
|
"image_path": "./data/IIIT5K/test/67_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "television",
|
|
"gt_answers": "TELEVISED",
|
|
"image_path": "./data/IIIT5K/test/67_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/681_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/681_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/681_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/681_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAY",
|
|
"image_path": "./data/IIIT5K/test/681_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ORIGINAL",
|
|
"image_path": "./data/IIIT5K/test/682_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARTIST",
|
|
"image_path": "./data/IIIT5K/test/682_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REPRODUCTION",
|
|
"image_path": "./data/IIIT5K/test/682_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RIGHTS",
|
|
"image_path": "./data/IIIT5K/test/682_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OBTAINABLE",
|
|
"image_path": "./data/IIIT5K/test/682_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POLICE",
|
|
"image_path": "./data/IIIT5K/test/683_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "targeting",
|
|
"gt_answers": "TARGETING",
|
|
"image_path": "./data/IIIT5K/test/683_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ILL",
|
|
"image_path": "./data/IIIT5K/test/683_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INFORMED",
|
|
"image_path": "./data/IIIT5K/test/683_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "me",
|
|
"gt_answers": "ME",
|
|
"image_path": "./data/IIIT5K/test/684_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BOB",
|
|
"image_path": "./data/IIIT5K/test/684_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/684_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CERTIFIED",
|
|
"image_path": "./data/IIIT5K/test/685_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PREOWNED",
|
|
"image_path": "./data/IIIT5K/test/685_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "19TH",
|
|
"image_path": "./data/IIIT5K/test/685_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SMBMWCOM",
|
|
"image_path": "./data/IIIT5K/test/685_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/685_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cars",
|
|
"gt_answers": "CARS",
|
|
"image_path": "./data/IIIT5K/test/685_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CENTER",
|
|
"image_path": "./data/IIIT5K/test/686_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "9080",
|
|
"image_path": "./data/IIIT5K/test/686_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BLOOMFIELD",
|
|
"image_path": "./data/IIIT5K/test/686_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mr",
|
|
"gt_answers": "MR",
|
|
"image_path": "./data/IIIT5K/test/688_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TRAFFIC",
|
|
"image_path": "./data/IIIT5K/test/688_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cop",
|
|
"gt_answers": "COP",
|
|
"image_path": "./data/IIIT5K/test/688_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "police",
|
|
"gt_answers": "POLICE",
|
|
"image_path": "./data/IIIT5K/test/688_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TRAFFIC",
|
|
"image_path": "./data/IIIT5K/test/689_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COP",
|
|
"image_path": "./data/IIIT5K/test/689_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "find",
|
|
"gt_answers": "FIND",
|
|
"image_path": "./data/IIIT5K/test/68_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/68_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "beach",
|
|
"gt_answers": "BEACH",
|
|
"image_path": "./data/IIIT5K/test/68_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLY",
|
|
"image_path": "./data/IIIT5K/test/696_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "99",
|
|
"image_path": "./data/IIIT5K/test/696_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PER",
|
|
"image_path": "./data/IIIT5K/test/696_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAY",
|
|
"image_path": "./data/IIIT5K/test/696_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWW",
|
|
"image_path": "./data/IIIT5K/test/696_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CITY",
|
|
"image_path": "./data/IIIT5K/test/696_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/696_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOOK",
|
|
"image_path": "./data/IIIT5K/test/696_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mobile",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/696_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertising",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/696_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AND",
|
|
"image_path": "./data/IIIT5K/test/697_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PEOPLE",
|
|
"image_path": "./data/IIIT5K/test/697_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEAR",
|
|
"image_path": "./data/IIIT5K/test/697_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FOR",
|
|
"image_path": "./data/IIIT5K/test/697_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/697_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADVERTISE",
|
|
"image_path": "./data/IIIT5K/test/697_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "exit",
|
|
"gt_answers": "EXIT",
|
|
"image_path": "./data/IIIT5K/test/699_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POINT",
|
|
"image_path": "./data/IIIT5K/test/699_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "exit",
|
|
"gt_answers": "EXIT",
|
|
"image_path": "./data/IIIT5K/test/699_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FLAMMABLE",
|
|
"image_path": "./data/IIIT5K/test/699_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALARM",
|
|
"image_path": "./data/IIIT5K/test/699_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CALL",
|
|
"image_path": "./data/IIIT5K/test/699_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fly",
|
|
"gt_answers": "FLY",
|
|
"image_path": "./data/IIIT5K/test/69_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "america",
|
|
"gt_answers": "AMERICA",
|
|
"image_path": "./data/IIIT5K/test/69_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "like",
|
|
"gt_answers": "LIKE",
|
|
"image_path": "./data/IIIT5K/test/69_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "excel",
|
|
"gt_answers": "EXEC",
|
|
"image_path": "./data/IIIT5K/test/69_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pay",
|
|
"gt_answers": "PAY",
|
|
"image_path": "./data/IIIT5K/test/69_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "like",
|
|
"gt_answers": "LIKE",
|
|
"image_path": "./data/IIIT5K/test/69_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/69_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the temp",
|
|
"gt_answers": "TEMP",
|
|
"image_path": "./data/IIIT5K/test/69_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "virgin",
|
|
"gt_answers": "VIRGIN",
|
|
"image_path": "./data/IIIT5K/test/69_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/6_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHANDIGARH",
|
|
"image_path": "./data/IIIT5K/test/6_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/6_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/6_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/6_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AVAIL",
|
|
"image_path": "./data/IIIT5K/test/6_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PSEGMENT",
|
|
"image_path": "./data/IIIT5K/test/6_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PANJAB",
|
|
"image_path": "./data/IIIT5K/test/6_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNIVERSITY",
|
|
"image_path": "./data/IIIT5K/test/6_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/705_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "york",
|
|
"gt_answers": "YORK",
|
|
"image_path": "./data/IIIT5K/test/705_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "paris",
|
|
"gt_answers": "PARIS",
|
|
"image_path": "./data/IIIT5K/test/705_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "barcelona",
|
|
"gt_answers": "BARCELONE",
|
|
"image_path": "./data/IIIT5K/test/705_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/70_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the expendables",
|
|
"gt_answers": "EXPENDABLES",
|
|
"image_path": "./data/IIIT5K/test/70_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REGENCY",
|
|
"image_path": "./data/IIIT5K/test/70_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NO",
|
|
"image_path": "./data/IIIT5K/test/710_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMMISSION",
|
|
"image_path": "./data/IIIT5K/test/710_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PROPERTY",
|
|
"image_path": "./data/IIIT5K/test/710_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "drive",
|
|
"gt_answers": "DRIVE",
|
|
"image_path": "./data/IIIT5K/test/712_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/712_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/712_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CONSUMER",
|
|
"image_path": "./data/IIIT5K/test/712_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/712_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/712_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/712_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MESSAGE",
|
|
"image_path": "./data/IIIT5K/test/712_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/715_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/715_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fashion",
|
|
"gt_answers": "FASHION",
|
|
"image_path": "./data/IIIT5K/test/715_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THIS",
|
|
"image_path": "./data/IIIT5K/test/715_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/716_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "extension",
|
|
"gt_answers": "EXTENSION",
|
|
"image_path": "./data/IIIT5K/test/716_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COUNTER",
|
|
"image_path": "./data/IIIT5K/test/716_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RELIANCE",
|
|
"image_path": "./data/IIIT5K/test/719_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDUSTRIES",
|
|
"image_path": "./data/IIIT5K/test/719_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIMITED",
|
|
"image_path": "./data/IIIT5K/test/719_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "M",
|
|
"image_path": "./data/IIIT5K/test/724_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YEAR",
|
|
"image_path": "./data/IIIT5K/test/725_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "summer",
|
|
"gt_answers": "SUMMER",
|
|
"image_path": "./data/IIIT5K/test/726_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "centre",
|
|
"gt_answers": "CENTRE",
|
|
"image_path": "./data/IIIT5K/test/726_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREEN",
|
|
"image_path": "./data/IIIT5K/test/728_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "green leaf",
|
|
"gt_answers": "LEAF",
|
|
"image_path": "./data/IIIT5K/test/728_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "joe's",
|
|
"gt_answers": "JOES",
|
|
"image_path": "./data/IIIT5K/test/72_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "it is a sign",
|
|
"gt_answers": "WHETLEY",
|
|
"image_path": "./data/IIIT5K/test/731_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "in the comments",
|
|
"gt_answers": "ARDON",
|
|
"image_path": "./data/IIIT5K/test/731_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hill",
|
|
"gt_answers": "HILL",
|
|
"image_path": "./data/IIIT5K/test/731_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "west",
|
|
"gt_answers": "WEST",
|
|
"image_path": "./data/IIIT5K/test/731_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "bridgeport",
|
|
"gt_answers": "BRIDPORT",
|
|
"image_path": "./data/IIIT5K/test/731_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PORCORUM",
|
|
"image_path": "./data/IIIT5K/test/731_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "newton",
|
|
"gt_answers": "NEWTON",
|
|
"image_path": "./data/IIIT5K/test/731_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRIDGE",
|
|
"image_path": "./data/IIIT5K/test/732_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMPANY",
|
|
"image_path": "./data/IIIT5K/test/732_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "powder",
|
|
"gt_answers": "POWDERS",
|
|
"image_path": "./data/IIIT5K/test/732_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SAUCES",
|
|
"image_path": "./data/IIIT5K/test/732_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RAS",
|
|
"image_path": "./data/IIIT5K/test/735_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AL",
|
|
"image_path": "./data/IIIT5K/test/735_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "horse power",
|
|
"gt_answers": "HORSEPOWER",
|
|
"image_path": "./data/IIIT5K/test/739_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/739_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/739_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "prepare",
|
|
"gt_answers": "PREPARE",
|
|
"image_path": "./data/IIIT5K/test/73_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EVIL",
|
|
"image_path": "./data/IIIT5K/test/73_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXES",
|
|
"image_path": "./data/IIIT5K/test/73_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/73_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FEEL",
|
|
"image_path": "./data/IIIT5K/test/73_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/73_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/73_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/73_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the league",
|
|
"gt_answers": "LEAGUE",
|
|
"image_path": "./data/IIIT5K/test/73_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/73_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MORE",
|
|
"image_path": "./data/IIIT5K/test/741_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HITS",
|
|
"image_path": "./data/IIIT5K/test/741_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THAN",
|
|
"image_path": "./data/IIIT5K/test/741_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOOGLE",
|
|
"image_path": "./data/IIIT5K/test/741_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIGHT",
|
|
"image_path": "./data/IIIT5K/test/742_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sponsor",
|
|
"gt_answers": "SPONSOR",
|
|
"image_path": "./data/IIIT5K/test/742_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NFL",
|
|
"image_path": "./data/IIIT5K/test/742_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "crew",
|
|
"gt_answers": "CREW",
|
|
"image_path": "./data/IIIT5K/test/745_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "40",
|
|
"image_path": "./data/IIIT5K/test/747_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOUCHDOWN",
|
|
"image_path": "./data/IIIT5K/test/748_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NSERIES",
|
|
"image_path": "./data/IIIT5K/test/753_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FEATURING",
|
|
"image_path": "./data/IIIT5K/test/754_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WEST",
|
|
"image_path": "./data/IIIT5K/test/754_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/756_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/756_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FAST",
|
|
"image_path": "./data/IIIT5K/test/756_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mobile",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/756_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADS",
|
|
"image_path": "./data/IIIT5K/test/756_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LET",
|
|
"image_path": "./data/IIIT5K/test/756_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRE",
|
|
"image_path": "./data/IIIT5K/test/759_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FLY",
|
|
"image_path": "./data/IIIT5K/test/759_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRE",
|
|
"image_path": "./data/IIIT5K/test/759_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FLY",
|
|
"image_path": "./data/IIIT5K/test/759_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AIR",
|
|
"image_path": "./data/IIIT5K/test/763_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/763_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/764_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "account",
|
|
"gt_answers": "ACCOUNT",
|
|
"image_path": "./data/IIIT5K/test/764_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wooden",
|
|
"gt_answers": "WOODEN",
|
|
"image_path": "./data/IIIT5K/test/767_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGN",
|
|
"image_path": "./data/IIIT5K/test/767_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "board",
|
|
"gt_answers": "BOARD",
|
|
"image_path": "./data/IIIT5K/test/767_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/768_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ORIGINAL",
|
|
"image_path": "./data/IIIT5K/test/768_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mobi",
|
|
"gt_answers": "MOBI",
|
|
"image_path": "./data/IIIT5K/test/770_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertising",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/770_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AL",
|
|
"image_path": "./data/IIIT5K/test/771_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COMMITMENT",
|
|
"image_path": "./data/IIIT5K/test/771_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/771_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ACTION",
|
|
"image_path": "./data/IIIT5K/test/771_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ASSISTANCE",
|
|
"image_path": "./data/IIIT5K/test/771_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COUNTRY",
|
|
"image_path": "./data/IIIT5K/test/771_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLOTHING",
|
|
"image_path": "./data/IIIT5K/test/771_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OUR",
|
|
"image_path": "./data/IIIT5K/test/771_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mckinney",
|
|
"gt_answers": "MCKINNEY",
|
|
"image_path": "./data/IIIT5K/test/772_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "T",
|
|
"image_path": "./data/IIIT5K/test/774_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WEBS",
|
|
"image_path": "./data/IIIT5K/test/775_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "life",
|
|
"gt_answers": "LIFE",
|
|
"image_path": "./data/IIIT5K/test/777_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "life comes",
|
|
"gt_answers": "COMES",
|
|
"image_path": "./data/IIIT5K/test/777_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DROPPED",
|
|
"image_path": "./data/IIIT5K/test/778_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "awas",
|
|
"gt_answers": "AWAS",
|
|
"image_path": "./data/IIIT5K/test/779_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RENT",
|
|
"image_path": "./data/IIIT5K/test/780_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "auction",
|
|
"gt_answers": "AUCTION",
|
|
"image_path": "./data/IIIT5K/test/783_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MINIMUM",
|
|
"image_path": "./data/IIIT5K/test/783_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BIDS",
|
|
"image_path": "./data/IIIT5K/test/783_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BULLPEN",
|
|
"image_path": "./data/IIIT5K/test/786_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MARKET",
|
|
"image_path": "./data/IIIT5K/test/786_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "POSTER",
|
|
"image_path": "./data/IIIT5K/test/790_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ITS",
|
|
"image_path": "./data/IIIT5K/test/791_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEDS",
|
|
"image_path": "./data/IIIT5K/test/791_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INSTORE",
|
|
"image_path": "./data/IIIT5K/test/791_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PET",
|
|
"image_path": "./data/IIIT5K/test/791_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cold",
|
|
"gt_answers": "COLD",
|
|
"image_path": "./data/IIIT5K/test/791_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AS",
|
|
"image_path": "./data/IIIT5K/test/791_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/791_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUG",
|
|
"image_path": "./data/IIIT5K/test/791_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sleds",
|
|
"gt_answers": "SLEDS",
|
|
"image_path": "./data/IIIT5K/test/792_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ARM",
|
|
"image_path": "./data/IIIT5K/test/794_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOURSELF",
|
|
"image_path": "./data/IIIT5K/test/794_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AGAIN",
|
|
"image_path": "./data/IIIT5K/test/795_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "made",
|
|
"gt_answers": "MADE",
|
|
"image_path": "./data/IIIT5K/test/796_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/796_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "india",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/799_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "gujarat",
|
|
"gt_answers": "GUJARAT",
|
|
"image_path": "./data/IIIT5K/test/799_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UNIVERSITY",
|
|
"image_path": "./data/IIIT5K/test/799_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "led",
|
|
"gt_answers": "LED",
|
|
"image_path": "./data/IIIT5K/test/804_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "writeable",
|
|
"gt_answers": "WRITABLE",
|
|
"image_path": "./data/IIIT5K/test/804_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "board",
|
|
"gt_answers": "BOARD",
|
|
"image_path": "./data/IIIT5K/test/804_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hootie",
|
|
"gt_answers": "HOOTIE",
|
|
"image_path": "./data/IIIT5K/test/805_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/812_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "24",
|
|
"image_path": "./data/IIIT5K/test/813_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOURS",
|
|
"image_path": "./data/IIIT5K/test/813_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ATM",
|
|
"image_path": "./data/IIIT5K/test/813_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "floor",
|
|
"gt_answers": "FLOOR",
|
|
"image_path": "./data/IIIT5K/test/814_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SBI",
|
|
"image_path": "./data/IIIT5K/test/815_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ATM",
|
|
"image_path": "./data/IIIT5K/test/815_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "can",
|
|
"gt_answers": "CAN",
|
|
"image_path": "./data/IIIT5K/test/817_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IT",
|
|
"image_path": "./data/IIIT5K/test/819_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tata",
|
|
"gt_answers": "TATA",
|
|
"image_path": "./data/IIIT5K/test/820_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NISSAN",
|
|
"image_path": "./data/IIIT5K/test/821_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/824_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/824_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/824_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THAN",
|
|
"image_path": "./data/IIIT5K/test/826_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/826_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THINK",
|
|
"image_path": "./data/IIIT5K/test/826_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/830_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/830_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/830_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OFFICE",
|
|
"image_path": "./data/IIIT5K/test/830_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEING",
|
|
"image_path": "./data/IIIT5K/test/830_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TAKEN",
|
|
"image_path": "./data/IIIT5K/test/830_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/831_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/831_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/831_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/831_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GO",
|
|
"image_path": "./data/IIIT5K/test/832_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GREEN",
|
|
"image_path": "./data/IIIT5K/test/832_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FUND",
|
|
"image_path": "./data/IIIT5K/test/834_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/838_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/838_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "A",
|
|
"image_path": "./data/IIIT5K/test/839_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOOD",
|
|
"image_path": "./data/IIIT5K/test/839_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RADIO",
|
|
"image_path": "./data/IIIT5K/test/839_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "UMLEITUNG",
|
|
"image_path": "./data/IIIT5K/test/841_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEST",
|
|
"image_path": "./data/IIIT5K/test/844_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MONEY",
|
|
"image_path": "./data/IIIT5K/test/844_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXTRA",
|
|
"image_path": "./data/IIIT5K/test/846_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VEDETT",
|
|
"image_path": "./data/IIIT5K/test/846_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BLOND",
|
|
"image_path": "./data/IIIT5K/test/846_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ENABLE",
|
|
"image_path": "./data/IIIT5K/test/850_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIRTUAL",
|
|
"image_path": "./data/IIIT5K/test/850_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KEYBOARD",
|
|
"image_path": "./data/IIIT5K/test/850_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IN",
|
|
"image_path": "./data/IIIT5K/test/850_19.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PASSWORD",
|
|
"image_path": "./data/IIIT5K/test/850_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MANAGEMENT",
|
|
"image_path": "./data/IIIT5K/test/850_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOGIN",
|
|
"image_path": "./data/IIIT5K/test/850_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/850_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLINE",
|
|
"image_path": "./data/IIIT5K/test/850_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/851_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/851_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/851_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GOLDEN",
|
|
"image_path": "./data/IIIT5K/test/853_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COLOUR",
|
|
"image_path": "./data/IIIT5K/test/853_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HIDLY",
|
|
"image_path": "./data/IIIT5K/test/854_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/854_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/854_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BIKE",
|
|
"image_path": "./data/IIIT5K/test/854_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TEA",
|
|
"image_path": "./data/IIIT5K/test/854_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/854_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GARDEN",
|
|
"image_path": "./data/IIIT5K/test/855_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LIVENATIONCOM",
|
|
"image_path": "./data/IIIT5K/test/855_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "madonna",
|
|
"gt_answers": "MADONNA",
|
|
"image_path": "./data/IIIT5K/test/855_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STICKY",
|
|
"image_path": "./data/IIIT5K/test/855_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SWEET",
|
|
"image_path": "./data/IIIT5K/test/855_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOUR",
|
|
"image_path": "./data/IIIT5K/test/855_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OCTOBER",
|
|
"image_path": "./data/IIIT5K/test/855_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "15",
|
|
"image_path": "./data/IIIT5K/test/855_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "pt",
|
|
"gt_answers": "PT",
|
|
"image_path": "./data/IIIT5K/test/857_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is umat",
|
|
"gt_answers": "TAMU",
|
|
"image_path": "./data/IIIT5K/test/857_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HARAP",
|
|
"image_path": "./data/IIIT5K/test/857_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAPOR",
|
|
"image_path": "./data/IIIT5K/test/857_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AIR",
|
|
"image_path": "./data/IIIT5K/test/857_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MINUM",
|
|
"image_path": "./data/IIIT5K/test/857_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NON",
|
|
"image_path": "./data/IIIT5K/test/857_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AIR",
|
|
"image_path": "./data/IIIT5K/test/857_27.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "max",
|
|
"gt_answers": "MAX",
|
|
"image_path": "./data/IIIT5K/test/857_28.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "height",
|
|
"gt_answers": "HEIGHT",
|
|
"image_path": "./data/IIIT5K/test/857_29.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "P",
|
|
"image_path": "./data/IIIT5K/test/857_34.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OFFICE",
|
|
"image_path": "./data/IIIT5K/test/857_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/857_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VISITORS",
|
|
"image_path": "./data/IIIT5K/test/857_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NEXT",
|
|
"image_path": "./data/IIIT5K/test/858_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "exit",
|
|
"gt_answers": "EXIT",
|
|
"image_path": "./data/IIIT5K/test/858_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FUEL",
|
|
"image_path": "./data/IIIT5K/test/858_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "24",
|
|
"image_path": "./data/IIIT5K/test/858_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HRS",
|
|
"image_path": "./data/IIIT5K/test/858_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TWITTERCOMAPLUSK",
|
|
"image_path": "./data/IIIT5K/test/859_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "twitter",
|
|
"gt_answers": "TWITTER",
|
|
"image_path": "./data/IIIT5K/test/859_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADAMS",
|
|
"image_path": "./data/IIIT5K/test/860_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "media motion",
|
|
"gt_answers": "MEDIAMOTION",
|
|
"image_path": "./data/IIIT5K/test/862_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "lower",
|
|
"gt_answers": "LOWER",
|
|
"image_path": "./data/IIIT5K/test/866_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COST",
|
|
"image_path": "./data/IIIT5K/test/866_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ASK",
|
|
"image_path": "./data/IIIT5K/test/866_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CO",
|
|
"image_path": "./data/IIIT5K/test/873_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZA",
|
|
"image_path": "./data/IIIT5K/test/873_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "0726813427",
|
|
"image_path": "./data/IIIT5K/test/873_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ELECT",
|
|
"image_path": "./data/IIIT5K/test/874_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "virginia",
|
|
"gt_answers": "VIRGINIA",
|
|
"image_path": "./data/IIIT5K/test/874_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MADUENO",
|
|
"image_path": "./data/IIIT5K/test/874_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/874_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "REACH",
|
|
"image_path": "./data/IIIT5K/test/875_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "100000",
|
|
"image_path": "./data/IIIT5K/test/875_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JUST",
|
|
"image_path": "./data/IIIT5K/test/875_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AED",
|
|
"image_path": "./data/IIIT5K/test/875_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "1000",
|
|
"image_path": "./data/IIIT5K/test/875_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WE",
|
|
"image_path": "./data/IIIT5K/test/878_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOO",
|
|
"image_path": "./data/IIIT5K/test/878_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "smile",
|
|
"gt_answers": "SMILE",
|
|
"image_path": "./data/IIIT5K/test/878_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "factory",
|
|
"gt_answers": "FACTORY",
|
|
"image_path": "./data/IIIT5K/test/881_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SALE",
|
|
"image_path": "./data/IIIT5K/test/881_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "chemistry",
|
|
"gt_answers": "CHEMIST",
|
|
"image_path": "./data/IIIT5K/test/882_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPEN",
|
|
"image_path": "./data/IIIT5K/test/882_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "24",
|
|
"image_path": "./data/IIIT5K/test/882_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOURS",
|
|
"image_path": "./data/IIIT5K/test/882_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "2NDS",
|
|
"image_path": "./data/IIIT5K/test/883_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORLD",
|
|
"image_path": "./data/IIIT5K/test/883_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SHOP",
|
|
"image_path": "./data/IIIT5K/test/883_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLINE",
|
|
"image_path": "./data/IIIT5K/test/883_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AUTOSPORTS",
|
|
"image_path": "./data/IIIT5K/test/884_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "is grouped",
|
|
"gt_answers": "GROUPED",
|
|
"image_path": "./data/IIIT5K/test/885_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/890_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIASBIN",
|
|
"image_path": "./data/IIIT5K/test/890_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/891_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CHURCH",
|
|
"image_path": "./data/IIIT5K/test/891_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "love",
|
|
"gt_answers": "LOVE",
|
|
"image_path": "./data/IIIT5K/test/891_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "always",
|
|
"gt_answers": "ALWAYS",
|
|
"image_path": "./data/IIIT5K/test/891_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BREAST",
|
|
"image_path": "./data/IIIT5K/test/893_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "cancer canada",
|
|
"gt_answers": "CANCERCA",
|
|
"image_path": "./data/IIIT5K/test/893_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/894_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/894_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIRST",
|
|
"image_path": "./data/IIIT5K/test/895_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AID",
|
|
"image_path": "./data/IIIT5K/test/895_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CITY",
|
|
"image_path": "./data/IIIT5K/test/896_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IDOLOBHA",
|
|
"image_path": "./data/IIIT5K/test/896_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LASETHEKWINI",
|
|
"image_path": "./data/IIIT5K/test/896_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WWWNONSTOPSIGNSCOM",
|
|
"image_path": "./data/IIIT5K/test/898_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/898_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TYPES",
|
|
"image_path": "./data/IIIT5K/test/898_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/898_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGNS",
|
|
"image_path": "./data/IIIT5K/test/898_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIGN",
|
|
"image_path": "./data/IIIT5K/test/898_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CRAVE",
|
|
"image_path": "./data/IIIT5K/test/899_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THE",
|
|
"image_path": "./data/IIIT5K/test/899_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WAVE",
|
|
"image_path": "./data/IIIT5K/test/899_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPEN",
|
|
"image_path": "./data/IIIT5K/test/901_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OWAKA",
|
|
"image_path": "./data/IIIT5K/test/902_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KM",
|
|
"image_path": "./data/IIIT5K/test/902_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIA",
|
|
"image_path": "./data/IIIT5K/test/902_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SOUTHERN",
|
|
"image_path": "./data/IIIT5K/test/902_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GLOBAL",
|
|
"image_path": "./data/IIIT5K/test/903_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZERO",
|
|
"image_path": "./data/IIIT5K/test/905_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BUENOS",
|
|
"image_path": "./data/IIIT5K/test/905_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "aires",
|
|
"gt_answers": "AIRES",
|
|
"image_path": "./data/IIIT5K/test/905_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NUEVO",
|
|
"image_path": "./data/IIIT5K/test/905_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EXPOSES",
|
|
"image_path": "./data/IIIT5K/test/907_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RIP",
|
|
"image_path": "./data/IIIT5K/test/907_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "curl",
|
|
"gt_answers": "CURL",
|
|
"image_path": "./data/IIIT5K/test/907_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KB",
|
|
"image_path": "./data/IIIT5K/test/909_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/909_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "new",
|
|
"gt_answers": "NEW",
|
|
"image_path": "./data/IIIT5K/test/909_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KBHOMECOM",
|
|
"image_path": "./data/IIIT5K/test/909_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "888KBHOMES",
|
|
"image_path": "./data/IIIT5K/test/909_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "sun",
|
|
"gt_answers": "SUN",
|
|
"image_path": "./data/IIIT5K/test/912_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MOBILE",
|
|
"image_path": "./data/IIIT5K/test/915_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/915_10.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GO",
|
|
"image_path": "./data/IIIT5K/test/915_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "billboard",
|
|
"gt_answers": "BILLBOARD",
|
|
"image_path": "./data/IIIT5K/test/915_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "advertising",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/915_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/915_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AD",
|
|
"image_path": "./data/IIIT5K/test/915_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/916_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/916_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/916_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RANCHI",
|
|
"image_path": "./data/IIIT5K/test/916_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "wait",
|
|
"gt_answers": "WAIT",
|
|
"image_path": "./data/IIIT5K/test/917_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LONGER",
|
|
"image_path": "./data/IIIT5K/test/917_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CENTRE",
|
|
"image_path": "./data/IIIT5K/test/918_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "fiery",
|
|
"gt_answers": "FIERY",
|
|
"image_path": "./data/IIIT5K/test/920_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CAN",
|
|
"image_path": "./data/IIIT5K/test/920_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "you",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/920_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "go",
|
|
"gt_answers": "GO",
|
|
"image_path": "./data/IIIT5K/test/920_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "KOYAH",
|
|
"image_path": "./data/IIIT5K/test/921_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RD",
|
|
"image_path": "./data/IIIT5K/test/921_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10050",
|
|
"image_path": "./data/IIIT5K/test/921_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RD",
|
|
"image_path": "./data/IIIT5K/test/922_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10000",
|
|
"image_path": "./data/IIIT5K/test/922_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "p pinang",
|
|
"gt_answers": "PPINANG",
|
|
"image_path": "./data/IIIT5K/test/922_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "JALAN",
|
|
"image_path": "./data/IIIT5K/test/923_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ROSS",
|
|
"image_path": "./data/IIIT5K/test/923_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "10450",
|
|
"image_path": "./data/IIIT5K/test/923_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PINANG",
|
|
"image_path": "./data/IIIT5K/test/923_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "mur",
|
|
"gt_answers": "MUR",
|
|
"image_path": "./data/IIIT5K/test/925_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DE",
|
|
"image_path": "./data/IIIT5K/test/925_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRETAGNE",
|
|
"image_path": "./data/IIIT5K/test/925_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ZIEHEN",
|
|
"image_path": "./data/IIIT5K/test/928_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEN",
|
|
"image_path": "./data/IIIT5K/test/928_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ERFOLG",
|
|
"image_path": "./data/IIIT5K/test/928_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COCACOLA",
|
|
"image_path": "./data/IIIT5K/test/929_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PHARMACY",
|
|
"image_path": "./data/IIIT5K/test/930_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BMW",
|
|
"image_path": "./data/IIIT5K/test/931_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/933_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/933_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEPOSIT",
|
|
"image_path": "./data/IIIT5K/test/933_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MILLENIUM",
|
|
"image_path": "./data/IIIT5K/test/933_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "state",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/934_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/934_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LAUNCHES",
|
|
"image_path": "./data/IIIT5K/test/934_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NRI",
|
|
"image_path": "./data/IIIT5K/test/934_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "27",
|
|
"image_path": "./data/IIIT5K/test/936_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PSD",
|
|
"image_path": "./data/IIIT5K/test/936_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SPORT",
|
|
"image_path": "./data/IIIT5K/test/938_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CLIPS",
|
|
"image_path": "./data/IIIT5K/test/938_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GUYS",
|
|
"image_path": "./data/IIIT5K/test/938_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAIRCUT",
|
|
"image_path": "./data/IIIT5K/test/938_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOWES",
|
|
"image_path": "./data/IIIT5K/test/939_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BILLBOARDS",
|
|
"image_path": "./data/IIIT5K/test/940_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADVERTISEMENTS",
|
|
"image_path": "./data/IIIT5K/test/940_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SILVER",
|
|
"image_path": "./data/IIIT5K/test/943_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOU",
|
|
"image_path": "./data/IIIT5K/test/944_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "QUIT",
|
|
"image_path": "./data/IIIT5K/test/944_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/944_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FEEL",
|
|
"image_path": "./data/IIIT5K/test/944_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THEY",
|
|
"image_path": "./data/IIIT5K/test/944_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WORK",
|
|
"image_path": "./data/IIIT5K/test/944_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEDIA",
|
|
"image_path": "./data/IIIT5K/test/945_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DRIVING",
|
|
"image_path": "./data/IIIT5K/test/945_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/945_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CASINO",
|
|
"image_path": "./data/IIIT5K/test/948_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "queen",
|
|
"gt_answers": "QUEEN",
|
|
"image_path": "./data/IIIT5K/test/948_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "jackson",
|
|
"gt_answers": "JACKSON",
|
|
"image_path": "./data/IIIT5K/test/949_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPEN",
|
|
"image_path": "./data/IIIT5K/test/949_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "24",
|
|
"gt_answers": "24",
|
|
"image_path": "./data/IIIT5K/test/949_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "rivers health",
|
|
"gt_answers": "HEALTH",
|
|
"image_path": "./data/IIIT5K/test/951_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "internal",
|
|
"gt_answers": "INTERNAL",
|
|
"image_path": "./data/IIIT5K/test/951_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "medicine",
|
|
"gt_answers": "MEDICINE",
|
|
"image_path": "./data/IIIT5K/test/951_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "group",
|
|
"gt_answers": "GROUP",
|
|
"image_path": "./data/IIIT5K/test/955_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOME",
|
|
"image_path": "./data/IIIT5K/test/957_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOAN",
|
|
"image_path": "./data/IIIT5K/test/957_16.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SCHEDULE",
|
|
"image_path": "./data/IIIT5K/test/957_17.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/957_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ABOUT",
|
|
"image_path": "./data/IIIT5K/test/957_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SERVICES",
|
|
"image_path": "./data/IIIT5K/test/957_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEPOSIT",
|
|
"image_path": "./data/IIIT5K/test/957_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SCHEMES",
|
|
"image_path": "./data/IIIT5K/test/957_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SERVICE",
|
|
"image_path": "./data/IIIT5K/test/958_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "welcome",
|
|
"gt_answers": "WELCOME",
|
|
"image_path": "./data/IIIT5K/test/958_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TO",
|
|
"image_path": "./data/IIIT5K/test/958_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOCATIONS",
|
|
"image_path": "./data/IIIT5K/test/958_18.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "loans",
|
|
"gt_answers": "LOANS",
|
|
"image_path": "./data/IIIT5K/test/958_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "GENERAL",
|
|
"image_path": "./data/IIIT5K/test/958_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANKING",
|
|
"image_path": "./data/IIIT5K/test/958_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SAMSUNG",
|
|
"image_path": "./data/IIIT5K/test/965_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "golden",
|
|
"gt_answers": "GOLDEN",
|
|
"image_path": "./data/IIIT5K/test/967_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPPORTUNITY",
|
|
"image_path": "./data/IIIT5K/test/967_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "parisian",
|
|
"gt_answers": "PARISIAN",
|
|
"image_path": "./data/IIIT5K/test/967_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COST",
|
|
"image_path": "./data/IIIT5K/test/969_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "all",
|
|
"gt_answers": "ALL",
|
|
"image_path": "./data/IIIT5K/test/969_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FIXTURES",
|
|
"image_path": "./data/IIIT5K/test/969_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MUST",
|
|
"image_path": "./data/IIIT5K/test/969_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "go",
|
|
"gt_answers": "GO",
|
|
"image_path": "./data/IIIT5K/test/969_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "start",
|
|
"gt_answers": "START",
|
|
"image_path": "./data/IIIT5K/test/970_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ADVERTISING",
|
|
"image_path": "./data/IIIT5K/test/970_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "today",
|
|
"gt_answers": "TODAY",
|
|
"image_path": "./data/IIIT5K/test/970_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "will",
|
|
"gt_answers": "WILL",
|
|
"image_path": "./data/IIIT5K/test/970_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "tell your kids",
|
|
"gt_answers": "YOUR",
|
|
"image_path": "./data/IIIT5K/test/970_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "the question",
|
|
"gt_answers": "CUSTOMERS",
|
|
"image_path": "./data/IIIT5K/test/970_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TU",
|
|
"image_path": "./data/IIIT5K/test/971_11.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "EQUIPO",
|
|
"image_path": "./data/IIIT5K/test/971_12.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "005216",
|
|
"image_path": "./data/IIIT5K/test/971_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MEXICO",
|
|
"image_path": "./data/IIIT5K/test/971_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "NOTICIAS",
|
|
"image_path": "./data/IIIT5K/test/971_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "62",
|
|
"image_path": "./data/IIIT5K/test/971_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "12PM",
|
|
"image_path": "./data/IIIT5K/test/971_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "hygienic",
|
|
"gt_answers": "HUYGENS",
|
|
"image_path": "./data/IIIT5K/test/972_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SIXTHSEAL",
|
|
"image_path": "./data/IIIT5K/test/972_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "COM",
|
|
"image_path": "./data/IIIT5K/test/972_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PACHA",
|
|
"image_path": "./data/IIIT5K/test/976_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HAVE",
|
|
"image_path": "./data/IIIT5K/test/977_13.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BEEN",
|
|
"image_path": "./data/IIIT5K/test/977_14.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "RESERVED",
|
|
"image_path": "./data/IIIT5K/test/977_15.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/977_20.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "WHITE",
|
|
"image_path": "./data/IIIT5K/test/977_21.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PERSONS",
|
|
"image_path": "./data/IIIT5K/test/977_22.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BY",
|
|
"image_path": "./data/IIIT5K/test/977_23.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ORDER",
|
|
"image_path": "./data/IIIT5K/test/977_24.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DEUR",
|
|
"image_path": "./data/IIIT5K/test/977_29.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BY",
|
|
"image_path": "./data/IIIT5K/test/977_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "blank",
|
|
"gt_answers": "BLANKES",
|
|
"image_path": "./data/IIIT5K/test/977_30.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HIERDIE",
|
|
"image_path": "./data/IIIT5K/test/977_31.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OPENBARE",
|
|
"image_path": "./data/IIIT5K/test/977_32.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "QAARVAN",
|
|
"image_path": "./data/IIIT5K/test/977_37.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "IS",
|
|
"image_path": "./data/IIIT5K/test/977_38.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "VIR",
|
|
"image_path": "./data/IIIT5K/test/977_39.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BLANKES",
|
|
"image_path": "./data/IIIT5K/test/977_44.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AANGEWYS",
|
|
"image_path": "./data/IIIT5K/test/977_45.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OP",
|
|
"image_path": "./data/IIIT5K/test/977_46.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "THESE",
|
|
"image_path": "./data/IIIT5K/test/977_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "public",
|
|
"gt_answers": "PUBLIC",
|
|
"image_path": "./data/IIIT5K/test/977_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "PREMISES",
|
|
"image_path": "./data/IIIT5K/test/977_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "STATE",
|
|
"image_path": "./data/IIIT5K/test/983_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BANK",
|
|
"image_path": "./data/IIIT5K/test/983_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "OF",
|
|
"image_path": "./data/IIIT5K/test/983_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INDIA",
|
|
"image_path": "./data/IIIT5K/test/983_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ELECTRIC",
|
|
"image_path": "./data/IIIT5K/test/984_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INC",
|
|
"image_path": "./data/IIIT5K/test/984_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ELECTRICAL",
|
|
"image_path": "./data/IIIT5K/test/984_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "CONTRACTOR",
|
|
"image_path": "./data/IIIT5K/test/984_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "7864260176",
|
|
"image_path": "./data/IIIT5K/test/984_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "adventure",
|
|
"gt_answers": "ADVENTURE",
|
|
"image_path": "./data/IIIT5K/test/984_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "video",
|
|
"gt_answers": "VIDEO",
|
|
"image_path": "./data/IIIT5K/test/985_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "coming",
|
|
"gt_answers": "COMING",
|
|
"image_path": "./data/IIIT5K/test/985_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "soon",
|
|
"gt_answers": "SOON",
|
|
"image_path": "./data/IIIT5K/test/985_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "winners",
|
|
"gt_answers": "WINNERS",
|
|
"image_path": "./data/IIIT5K/test/993_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "LOSERS",
|
|
"image_path": "./data/IIIT5K/test/993_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DOUG",
|
|
"image_path": "./data/IIIT5K/test/994_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "herbert",
|
|
"gt_answers": "HERBERT",
|
|
"image_path": "./data/IIIT5K/test/994_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SNAP",
|
|
"image_path": "./data/IIIT5K/test/994_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ON",
|
|
"image_path": "./data/IIIT5K/test/994_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TOP",
|
|
"image_path": "./data/IIIT5K/test/994_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "FUEL",
|
|
"image_path": "./data/IIIT5K/test/994_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "dragster",
|
|
"gt_answers": "DRAGSTER",
|
|
"image_path": "./data/IIIT5K/test/994_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "SNAPON",
|
|
"image_path": "./data/IIIT5K/test/994_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BRISTOL",
|
|
"image_path": "./data/IIIT5K/test/997_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "BAY",
|
|
"image_path": "./data/IIIT5K/test/997_2.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INSURANCE",
|
|
"image_path": "./data/IIIT5K/test/997_3.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "INCOME",
|
|
"image_path": "./data/IIIT5K/test/997_4.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "TAX",
|
|
"image_path": "./data/IIIT5K/test/997_5.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "ONLY",
|
|
"image_path": "./data/IIIT5K/test/997_8.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "DAY",
|
|
"image_path": "./data/IIIT5K/test/997_9.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "HOW",
|
|
"image_path": "./data/IIIT5K/test/999_1.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "AT",
|
|
"image_path": "./data/IIIT5K/test/999_6.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "70",
|
|
"image_path": "./data/IIIT5K/test/999_7.png",
|
|
"model_name": "BLIP2"
|
|
},
|
|
{
|
|
"question": "what is written in the image?",
|
|
"answer": "",
|
|
"gt_answers": "MPH",
|
|
"image_path": "./data/IIIT5K/test/999_8.png",
|
|
"model_name": "BLIP2"
|
|
}
|
|
] |