search

NVlabs / GroupViT

Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.
https://arxiv.org/abs/2202.11094
Other
725 stars 52 forks source link

Do you use "raw_caption" or "caption" as the caption in RedCaps12m? #47

Closed yxchng closed 1 year ago

yxchng commented 1 year ago

RedCaps12m has "raw_caption" and "caption" in its annotations. Can I know which one do you use?

xvjiarui commented 1 year ago

Hi @yxchng I use "caption".

Please refer to conversion script for details https://github.com/NVlabs/GroupViT/blob/13b786155a1dfffe4703f40d028c92be58e1178d/convert_dataset/process_redcaps.py#L41