how many training instances are used?

open-mmlab / Multimodal-GPT

Multimodal-GPT

Apache License 2.0

1.48k stars 126 forks source link

how many training instances are used? #14

Open TobiasLee opened 1 year ago

TobiasLee commented 1 year ago

Hi, thanks for your great project! I am wondering how many training dataset instances you are used, such as COCO, OCR-VQA and A-OKVQA, did you just transform the original dataset with the template so the numbers are consistent with the original dataset?

TobiasLee commented 1 year ago

I see the paper mention that 5k coco caption-image pair and 512 OCR, A-OKVQA pairs are used. so if I am correct,y except for the LLAVA and minigpt4, there are 6k instances?