Issues
- 1
Why noise is added to “prefix”(visual embeding by clip) instead of token(text embeding by tokenizer)in the code?
#19 opened by Panlizhi - 0
- 1
modality_offset
#14 opened by Flaick - 6
- 1
how to get train.json?
#13 opened by qq123aa456 - 1
About FlickrStyle10K
#12 opened by LiLiParty - 5
- 2
training parameters on Flickr30k dataset
#11 opened by mzhaoshuai - 1
- 1
about the parameters of train.py
#8 opened by tianguang2525 - 1
Different results at CiDER metric in paper
#6 opened by taewhankim - 1
About the type of gpt2
#4 opened by zjr2000 - 1
annotations files of coco during evaluation
#5 opened by mzhaoshuai - 3
About the variance of 0.016
#3 opened by 232525 - 3
Requirements File
#2 opened by Adesoji1