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

请教数据预处理部分 #1

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

请教数据预处理部分 #1

Decalogue opened this issue Nov 5, 2018 · 5 comments

Comments

@Decalogue
Copy link

Decalogue commented Nov 5, 2018

您好!
看了您的项目收获很大,非常感谢!请问您数据预处理部分有开源吗?我在尝试跑的时候发现 train.json 应该是处理过的,而且有些属性是原数据集中没有的。请问方便分享吗?
多谢了!

@Decalogue
Copy link
Author

另外词向量是要自己根据数据集训练吗?

@freefuiiismyname
Copy link
Owner

你好,1、运行本模型,需要对源数据分词(包括query、passage、alternatives)。由于本次以分享思路为主,并没有开源数据预处理部分的计划。2、基于数据集训练的词向量就好,如果追求更好的效果,可以使用外部词向量。

@Decalogue
Copy link
Author

多谢了!

@KonroyZhu
Copy link

您好!
我在尝试运行模型,但是遇到了 tensorflow的报错
“could not convert BatchDescriptor {count: 64 feature_map_count: 300 spatial: 0 1 value_min: 0.000000 value_max: 0.000000 layout: BatchDepthYX} ”
请问有人遇到过类似的情况吗?

@fooSynaptic
Copy link

哇,不能直接跑的项目可真是让人一眼难尽呢

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

4 participants