salesforce / BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
BSD 3-Clause "New" or "Revised" License
4.85k stars 648 forks source link

How to train BLIP to generate embeddings for new image-text pairs? #69

Open smith-co opened 2 years ago

smith-co commented 2 years ago

How to fine tune BLIP to generate embeddings for new image-text pairs? Can anyone provide me with code snippets or examples?