muzairkhattak / multimodal-prompt-learning

[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".
https://muzairkhattak.github.io/multimodal-prompt-learning/
MIT License
635 stars 48 forks source link

Where is the innovation point #70

Closed zbb1111 closed 2 months ago

zbb1111 commented 3 months ago

Thank you very much for your excellent article. I would like to ask about the modification and innovation of clip, specifically in which position in the code. As a beginner, I really hope to receive your help! Looking forward to your reply, thank you!

muzairkhattak commented 3 months ago

Hi @zbb1111,

Thank you for showing interest in MaPLe!

Regarding your query, please note that our MaPLe framework has been implemented in the following parts of the code:

1) MaPLe trainer: maple.py 2) Vision-Language deep prompting: clip/model.py

You can checkout these code files for the main implementation of MaPLe framework. Let us know if there are any further questions. Thank you and kind regards!

muzairkhattak commented 2 months ago

Hi @zbb1111,

I am closing the issue now. Feel free to open it if there are still any issues.