CLIP-rsicd Remote sensing image captioning

Thanks for your excellent work! This pretraining work is done on three RSICD and how can the code directly be used to generate captions on these RSICD? Could you please give me some instructions? thanks a lot again!

May 09 '22 01:05 Waiting-TT

Hello. Thanks for your interest. The CLIP model cannot be used to generate captions directly. We have plans to add a finetuned prefix GPT or similar model at some point for captioning. But there is no ETA for it as of now. You can try out the approach described here https://github.com/rmokady/CLIP_prefix_caption.

May 14 '22 14:05 arampacha

Thanks for your reply!

从 Windows 版邮件发送

发件人: arampacha 发送时间: 2022年5月14日 22:09 收件人: arampacha/CLIP-rsicd 抄送: Waiting-TT; Author 主题: Re: [arampacha/CLIP-rsicd] Remote sensing image captioning (Issue#39)

Hello. Thanks for your interest. The CLIP model cannot be used to generate captions directly. We have plans to add a finetuned prefix GPT or similar model at some point for captioning. But there is no ETA for it as of now. You can try out the approach described here https://github.com/rmokady/CLIP_prefix_caption. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

May 16 '22 00:05 Waiting-TT