About the pre-trained models of VQA-Rad and Slake

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

174 stars 11 forks source link

About the pre-trained models of VQA-Rad and Slake #13

Open luzimu opened 1 year ago

luzimu commented 1 year ago

Thanks for you marvelous work! Could you please consider releasing the pre-trained models for VQA-Rad and Slake? I encountered an issue in './src/MedVInT_TD/test_VQA_RAD.py' where I couldn't find the released model './Results/QA_no_pretrain_no_aug/VQA_RAD/checkpoint-16128' as specified in line 21. Your assistance with this would be greatly appreciated.

hncuong commented 1 year ago

Or could you please share the hyper-parameters that was used to fine-tune the pretrained checkpoint to achieve SOTA results on VQA RAD and SLAKE reported in the paper? Thanks and best regards!