search

xiaoman-zhang / PMC-VQA

PMC-VQA is a large-scale medical visual question-answering dataset, which contains 227k VQA pairs of 149k images that cover various modalities or diseases.
MIT License
176 stars 11 forks source link

Fine-tuning on VQA-RAD & SLAKE datasets #1

Closed o0t1ng0o closed 1 year ago

o0t1ng0o commented 1 year ago

Hi @xiaoman-zhang,

Thank you for sharing this code of your interesting work PMC-VQA. I found that you reported the performance on VQA-RAD and SLAKE dataset. Could you provide the details about the finetuning on VQA-RAD and SLAKE dataset? Thank you in advance.

Best,

xiaoman-zhang commented 1 year ago

We have updated the finetune dataset and code in ./src/MedVInT_TE/

avi-otterai commented 1 year ago

Thanks @xiaoman-zhang for the code updates! Could you also please add or summarize the evaluation code for the two datasets using ACC metric as described in the paper?