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

默认参数batchsize为啥这么大，实验中越大越好吗 #11

Open
ysgncss opened this issue Nov 3, 2020 · 5 comments
Open

默认参数batchsize为啥这么大，实验中越大越好吗 #11

ysgncss opened this issue Nov 3, 2020 · 5 comments

Comments

@ysgncss
Copy link

ysgncss commented Nov 3, 2020

No description provided.

@Magicat128
Copy link
Collaborator

@ysgncss

你好，batch size大是因为：1. 计算效率高，减少训练时间；2. 训练震荡小，收敛速度快。

@ysgncss
Copy link
Author

ysgncss commented Dec 11, 2020

应用在中文数据集上不知道为啥，效果不太好

@ysgncss
Copy link
Author

ysgncss commented Dec 11, 2020

按照英文数据集一样的格式应该就行吧？分好词按空格隔开的

@Magicat128
Copy link
Collaborator

你好，目前没有在中文数据集上试过，猜测可能与分词的处理有关（考虑到中文以词组的形式比较多）。

@zsaaaaaaa
Copy link

空格
你好，你在中文数据集上效果一直不好吗，你做的是中文文本分类吗

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
3 participants
@ysgncss @Magicat128 @zsaaaaaaa