LAVIS
LAVIS copied to clipboard
Load finetuned huggingface model/ generate embeddings
I finetuned "Salesforce/blip-image-captioning-base" model at huggingface.
I want to use the finetune model to generate feature vectors of images/ texts, but When I loaded it I found that it doesn't have the method "extract_features"
How could I do that?
same problem here, did you figure out a way to do that?