Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

去除transformAttention评估模型时,是怎么处理维度不匹配的问题的? #16

Open
shuqincao opened this issue Aug 12, 2020 · 6 comments

Comments

@shuqincao
Copy link

为了研究模型中各部分的影响,作者去除了transformAttention部分来评估模型性能,如果直接将此部分的代码注释,在执行decoder部分的spatialAttention的 X = tf.concat((X, STE), axis = -1)这一行代码会报维度不匹配错误,所以想请教作者在去除transformAttention模块来评估模型的性能时,是如何处理维度的

@EmlynQuan
Copy link

您好,我想请教一下 作者原始的这个代码是如何跑通的?我在utils的73,74行 timeofday = (Time.hour * 3600 + Time.minute * 60 + Time.second) // Time.freq.delta.total_seconds() 这部分会报错 跪求指点😭

@flowingrain

This comment has been minimized.

@bingkuaibaoer
Copy link

您好,我想请教下 作者代码的而两个文件在那个位置啊 /data/pems-bay.h5 /data/GMAN.pkl

@shuqincao
Copy link
Author

shuqincao commented Apr 8, 2021 via email

@bingkuaibaoer
Copy link

bingkuaibaoer commented Apr 9, 2021 via email

@BeverlyZ
Copy link

BeverlyZ commented Mar 7, 2022

timeofday = (Time.hour * 3600 + Time.minute * 60 + Time.second)
// Time.freq.delta.total_seconds()
这一行同样会报错,求大神们指点!拜托了!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants