How to extract image embeddings and caption embeddings ? Thank you

[jkentmanning]

I am a student in Toronto learning about multimodal models and multimodal retrieval.
Can embeddings be extracted from your models ?
I would like to compare retrieval results from your model to CLIP.
Also, my Mandarin understanding is not good.
If you have time, if you could please provide some tutorial videos in english, I would be very grateful. Thank you for feedback. Thank you for publishing your work, which seems excellent! Regards, Kent

[wangruohui]

Hi,

You may refer to https://github.com/open-mmlab/mmpretrain?tab=readme-ov-file#model-zoo. There are some multimodal models.