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

复现结果较低 #29

Open
NonvolatileMemory opened this issue Mar 13, 2019 · 7 comments
Open

复现结果较低 #29

NonvolatileMemory opened this issue Mar 13, 2019 · 7 comments

Comments

@NonvolatileMemory
Copy link

哥们您好,我也是做nlp的。
自己尝试复现了一下,发现效果不好,我的结构就是q,a都过lstm(两边共享的参数),然后maxpooling得到向量,cos之后triplet loss,但是只跑到了0。5,而且跑得非常慢,我一个q采样了100个negative a,想问一下啊您的模型快不快呢?我大约要一天才能收敛,参数都是我从别人论文里面找来的。。。

@white127
Copy link
Owner

white127 commented Mar 13, 2019 via email

@NonvolatileMemory
Copy link
Author

感觉不是参数的问题,因为我都是用的一篇iclr的论文里面的,老哥我想问一下您的模型收敛的快吗?谢谢您的回复,十分感谢~

@NonvolatileMemory
Copy link
Author

不过我的框架也很您不太一样,我是用MXNET的,感觉这种数据集比较小,很有可能就出现这种问题

@white127
Copy link
Owner

white127 commented Mar 13, 2019 via email

@white127
Copy link
Owner

white127 commented Mar 13, 2019 via email

@NonvolatileMemory
Copy link
Author

那你很快了,我非常慢,可能是哪里有问题了

@NonvolatileMemory
Copy link
Author

非常感谢您的回复!!!如果有缘再现实生活中见面,请您吃饭哈哈哈

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