search

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
578 stars 43 forks source link

Where V-L coupling function? #75

Open Sandy-program opened 2 weeks ago

Sandy-program commented 2 weeks ago

Hi author, your work is excellent and I am very interested in your work. However, I have a question. As mentioned in your article, the first 8 layers of text prompts can provide visual prompts to the visual encoder through a V-L coupling function, but I have not found the corresponding implementation code for this place. Can you provide the corresponding code location for me? I am very grateful for that.

muzairkhattak commented 5 days ago

Hi @Sandy-program,

Thank you for showing interest in MaPLe!

Regarding your query, the corresponding code for the deep prompting at text side can be found at these lines.

I hope it is clear now.

Thank you and kind regards!