Closed Control-derek closed 1 year ago
Hi Authors,
How did you get cc3m_embeddings.npy ? Do you use the trained vision encoder and linear project layer? Or you only use the method of Vector database(I don't know about the Vector database at all)
Thank you!
Hi, I realized this script wasn't added before, so here it is now: https://github.com/kohjingyu/gill/blob/main/scripts/extract_img_embs.py
Hope that helps!
Hi Authors,
How did you get cc3m_embeddings.npy ? Do you use the trained vision encoder and linear project layer? Or you only use the method of Vector database(I don't know about the Vector database at all)
Thank you!