KM-BART
KM-BART copied to clipboard
KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
Hi! Thanks for your great work~ Would you consider providing the script or API that can directly and easily make inference on other datasets?
Hello, While reproducing KM-BART, I realize I cannot get the same score as proposed in the paper. Why?? Is there another script used to compute novel, unique scores?
Hi guys, Is this the resulting model of the pretraining step (i.e. prior to fine-tuning)?