RotsteinNoam/FuseCap
FuseCap: Large Language Model for Visual Data Fusion in Enriched Caption Generation
PythonMIT
Issues
- 0
Will whole code release?
#9 opened by yiranxie233 - 4
training and inference costs for fuser
#8 opened by YoojLee - 1
T5 LLMFuser weights release
#6 opened by rohit-gupta - 1
CLIPScore calculation
#7 opened by Fa-ti-ma - 1
When will the code be released?
#2 opened by linzhiqiu - 2
- 1
coco_karpathy_train.json is broken
#4 opened by ChrisLiu6 - 1
Unable to access the provided data
#3 opened by ChrisLiu6 - 1
about the enriched captions
#1 opened by wanboyang