search

gkw0010 / Surgical-LVLM

Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded VQA in Robotic Surgery
5 stars 1 forks source link

About the VP-LoRA #1

Open rhyhck opened 6 months ago

rhyhck commented 6 months ago

Hello author, thank you very much for sharing the code. I can not find the VP-LoRA and Projection Module mentioned in the article, could you give me some guidance?

gkw0010 commented 6 months ago

Thank you for your interests. vpl block is in https://github.com/gkw0010/Surgical-LVLM/blob/b8743083752b3313a9cde63fd832c0f4b55afbd0/vmamba.py#L269 It is used in https://github.com/gkw0010/Surgical-LVLM/blob/b8743083752b3313a9cde63fd832c0f4b55afbd0/galora.py#L74

rhyhck commented 6 months ago

OK, thank you for your help! I cann't find the Projection Module mentioned in the article as well, could you give me some guidance?

longbai-cuhk commented 4 months ago

Thank you for your interest. We are still working on extending this work and we will make code and data publicly accessible upon acceptance.