-
Notifications
You must be signed in to change notification settings - Fork 811
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
train 和eval时间 #152
Comments
我也想请教下,刚跑这个代码,不太懂eval是要和train同时跑么? |
不是,是分开跑的
发自我的iPhone
…------------------ 原始邮件 ------------------
发件人: trc <[email protected]>
发送时间: 2020年3月17日 02:53
收件人: abisee/pointer-generator <[email protected]>
抄送: jichangzhen <[email protected]>, Author <[email protected]>
主题: 回复:[abisee/pointer-generator] train 和eval时间 (#152)
我也想请教下,刚跑这个代码,不太懂eval是要和train同时跑么?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
论文中有详细说明: 数据集:CNN/Daily Mail
GPU型号:Tesla K40m GPU 超参数:
训练轮数及时间:
|
这个eval要跑到什么时候以及作用是什么,eval跑完了之后还需要在跑train吗?我这边是把train阶段终止了之后再去跑这个eval,发现log/eval目录下什么也没有呀,难道他的功能就只是保存最好的模型到log/train目录中吗? |
这个eval的意思是不是,只在测试集上计算了训练结束最后的一个模型? |
同问,这个eval要跑多久,作用是啥呢? |
不知道train 和eval到什么程度可以去解码,训练多长时间
The text was updated successfully, but these errors were encountered: