Twilighter9527

你绑定监听都两次了，第二次不就报错了吗

oh! thank you very much!!! ------------------ 原始邮件 ------------------ 发件人: "rmokady/CLIP_prefix_caption" ***@***.***>; 发送时间: 2022年3月25日(星期五) 上午6:21 ***@***.***>; 抄送: "pl0t-k ???? ?? ***@***.******@***.***>; 主题: Re: [rmokady/CLIP_prefix_caption] Evaluate problem (Issue #33) Hi @wytszhuzhu, we have used the Oscar evaluation...

> there is not space in train data.And when inference, it's just need the clip_embedding tensor,not need tha caption.isn't it? 

> I find that not all of your training caption end with the '.', since the end token for beamsearch is '.', thus the model may not know when to...

> I really want to know how you generate this caption, I am new to this direction, do not know how you run the result, I follow the readme run,...

Do you solve it? I have the same problem.