About sent_splits.mat

[NanAlbert]

Hello, I would like to know how to generate the file sent_splits.mat or where to get the file of other datasets, e.g., AwA2, SUN, APY.
Thank you so much!

[1maojian1]

@NanAlbert hello,I have the same problem，Have you solved it now？

[NanAlbert]

@NanAlbert hello,I have the same problem，Have you solved it now？

As I know so far, there is no CNN-RNN sentence embeddings for AwA2, SUN and APY datasets.

[1maojian1]

你好，请问您在AWA1，AWA2数据集中可以跑到论文中的效果吗？我按照作者给的参数在AWA1中只能跑到h= 67.5，论文中h = 69.1

…

------------------ 原始邮件 ------------------ 发件人: "Hanzy1996/CE-GZSL" ***@***.***>; 发送时间: 2022年7月24日(星期天) 晚上10:58 ***@***.***>; ***@***.******@***.***>; 主题: Re: [Hanzy1996/CE-GZSL] About sent_splits.mat (Issue #14) Closed #14 as completed. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***>

[rongtongxueya]

same question，How should such semantic data sets be generated，I want to build my own data set

[NanAlbert]

same question，How should such semantic data sets be generated，I want to build my own data set

As I mentioned before, there are no CNN-RNN sentence embeddings available for the AwA2, SUN, and APY datasets. However, you could consider using language models like BERT to generate semantic data for your own dataset.