search

jackroos / VL-BERT

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".
MIT License
738 stars 110 forks source link

fine-tune #70

Open cxjtju opened 3 years ago

cxjtju commented 3 years ago

I want to use VLBERT to fine-tune on multi-modal knowledge graph dataset, in which each entity has an image and a paragraph description. Can I use the pre-trained model to get the representation of each entity? And how do I load my dataset into the model? Thanks!

Ellyuca commented 1 year ago

Hi @cxjtju. Did you figure it out how to load your new dataset into the model? Thanks.