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.

Sign up for GitHub

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

Jump to bottom

你的textcnn实验，只要把学习率调大一个数量级，没有预训练也可以得到一样的结果 #18

Open
wykdg opened this issue Dec 5, 2018 · 5 comments
Open

你的textcnn实验，只要把学习率调大一个数量级，没有预训练也可以得到一样的结果 #18

wykdg opened this issue Dec 5, 2018 · 5 comments

Comments

@wykdg
Copy link

wykdg commented Dec 5, 2018

No description provided.

@myeclipse
Copy link

真相了。。。

@brightmart
Copy link
Owner

不会吧。使用大规模的语料预训练，对准确率提升没有帮助吗？

@wykdg
Copy link
Author

wykdg commented Dec 5, 2019

你这个实验调了一个非常小的学习率，导致没预训练的textcnn训练不起来而已。模型太小了，预训练的意义不大

@chenlin038
Copy link

textcnn如何预训练？我觉得这根本就不可行！
textcnn跟transformer结构不一样，textcnn经过卷积池化之后，所有的文本都表示成了一个向量，根本没法取出对应mask位置的词向量 作词表的映射，又谈何做mask工作？此外，bert_cnn_model.py 也没有预训练textcnn的code. @brightmart @wykdg

@wykdg
Copy link
Author

wykdg commented Apr 25, 2020

还有人at我。。。这个就是他前年蹭热点乱写的代码而已。。一点意义都没啊

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@myeclipse @wykdg @brightmart @chenlin038