-
Notifications
You must be signed in to change notification settings - Fork 282
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
如何预测 #21
Comments
可以增加一个前置的rank模块,用一个高性能、简单的算法进行答案初筛选 |
多谢回复,那么大概训练多少轮可以收敛呢?我这跑了几千轮好像变化不大 |
未收敛的一般原因
1. 模型有问题
2. 学习率设置不合理
2018-04-25 9:05 GMT+08:00 kscp123 <[email protected]>:
… 多谢回复,那么大概训练多少轮可以收敛呢?我这跑了几千轮好像变化不大
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#21 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ABffUIiNOuK98NFQcfnLE-yo61U3RjpTks5tr8u9gaJpZM4TSxiS>
.
|
这个确实是一般情况,但是在这个问题下好像不适用,因为这里跑的是你的代码,看到下面有人说10K+轮才开始有点效果,所以我就是想知道你跑了多少轮 @white127 |
差不多吧
在 2018年4月26日 上午10:43,kscp123 <[email protected]>写道:
… 这个确实是一般情况,但是在这个问题下好像不适用,因为这里跑的是你的代码,看到下面有人说10K+轮才开始有点效果,所以我就是想知道你跑了多少轮
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#21 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ABffUOSc3QLRkraNj51tUGLxmyw6xrOjks5tsTRMgaJpZM4TSxiS>
.
|
还有个疑问就是这段代码万一pos和neg采到同一个,那岂不是会影响训练?虽然概率很小 |
这个概率很小,直接忽略吧,影响不大
2018-04-27 8:51 GMT+08:00 kscp123 <[email protected]>:
… 还有个疑问就是这段代码万一pos和neg采到同一个,那岂不是会影响训练?虽然概率很小
pos = trainList[random.randint(0, len(trainList)-1)]
neg = trainList[random.randint(0, len(trainList)-1)]
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#21 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ABffUFyiHJOhC_vgEvczsy0BSWEZlfyJks5tsmuagaJpZM4TSxiS>
.
|
|
1.对 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
这个实际使用怎么预测?如果候选集的答案很多计算会很慢吧
The text was updated successfully, but these errors were encountered: