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

new model #27

Open
zemu121 opened this issue Nov 5, 2018 · 5 comments
Open

new model #27

zemu121 opened this issue Nov 5, 2018 · 5 comments

Comments

@zemu121
Copy link

zemu121 commented Nov 5, 2018

模型中只用了一层卷积,filter是(1,2,3,5)* embedding_size的,如果构建一般图像处理的模型呢,filter是个小滑窗(如5*5),多次conv+max_pool,这样的模型会有什么问题吗

@white127
Copy link
Owner

图像应该就是这样处理的吧

@zemu121
Copy link
Author

zemu121 commented Nov 21, 2018

对,如果这个模型也用类似于图像处理的方法,可以吗

@zemu121
Copy link
Author

zemu121 commented Nov 21, 2018

像您给出的滑窗,直接向后滑动1,2,3,5个字,这是可解释的,但是如果用小滑窗的话,就是单纯做特征工程,不可解释了

@white127
Copy link
Owner

没有具体做过图像的应用,但是我理解,滑动窗口的大小,在图像里面就表示你想要关注窗口内的像素点的关系,这个应该就是具体的可解释的意义,跟文字一样,我们关注多少个字之间的关系

@zemu121
Copy link
Author

zemu121 commented Nov 21, 2018

恩,对的,可以这样理解,我觉得之后可以尝试用图像的模型来做一下,比较一下效果,之后有结果,我再跟您update,多谢

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

2 participants