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

请问您给的训练策略能把模型loss收敛到多小? #11

Open
CWF-999 opened this issue Nov 1, 2019 · 12 comments
Open

请问您给的训练策略能把模型loss收敛到多小? #11

CWF-999 opened this issue Nov 1, 2019 · 12 comments

Comments

@CWF-999
Copy link

CWF-999 commented Nov 1, 2019

请问您给的训练策略能把模型loss收敛到多小?我顶天了到3.7左右就再也降不下去了,不管是加epoch,调整学习率,还是调整batch_size都无法降低了?请问这是什么原因呢?

@XinWangg
Copy link

XinWangg commented Nov 6, 2019

你训练几个epoch呢?

@CWF-999
Copy link
Author

CWF-999 commented Nov 6, 2019 via email

@XinWangg
Copy link

XinWangg commented Nov 6, 2019 via email

@CWF-999
Copy link
Author

CWF-999 commented Nov 6, 2019

我到3.62就开始跳动了,下不去了。给更小的学习率也没用

@XinWangg
Copy link

XinWangg commented Nov 6, 2019 via email

@CWF-999
Copy link
Author

CWF-999 commented Nov 6, 2019 via email

@liukaigua
Copy link

请问您给的训练策略能把模型loss收敛到多小?我顶天了到3.7左右就再也降不下去了,不管是加epoch,调整学习率,还是调整batch_size都无法降低了?请问这是什么原因呢?

请问你训练的是哪个数据集?我训练的VOC数据集,在VOC2007_test上的Loss最低也就降到4.36。

@CWF-999
Copy link
Author

CWF-999 commented Nov 18, 2019 via email

@liukaigua
Copy link

VOC2007 和VOC2012一起训练

------------------ 原始邮件 ------------------ 发件人: "lsccccc"<[email protected]>; 发送时间: 2019年11月18日(星期一) 中午11:48 收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>; 抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>; 主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小? (#11) 请问您给的训练策略能把模型loss收敛到多小?我顶天了到3.7左右就再也降不下去了,不管是加epoch,调整学习率,还是调整batch_size都无法降低了?请问这是什么原因呢? 请问你训练的是哪个数据集?我训练的VOC数据集,在VOC2007_test上的Loss最低也就降到4.36。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

还想请问一下您训练的学习率是多少,训练多少个epoch?不胜感激!

@CWF-999
Copy link
Author

CWF-999 commented Nov 18, 2019 via email

@liukaigua
Copy link

用的余弦退火学习率调整策略,300epoch,初始0.01

------------------ 原始邮件 ------------------ 发件人: "lsccccc"<[email protected]>; 发送时间: 2019年11月18日(星期一) 下午3:59 收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>; 抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>; 主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小? (#11) VOC2007 和VOC2012一起训练 … ------------------ 原始邮件 ------------------ 发件人: "lsccccc"<[email protected]>; 发送时间: 2019年11月18日(星期一) 中午11:48 收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>; 抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>; 主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小? (#11) 请问您给的训练策略能把模型loss收敛到多小?我顶天了到3.7左右就再也降不下去了,不管是加epoch,调整学习率,还是调整batch_size都无法降低了?请问这是什么原因呢? 请问你训练的是哪个数据集?我训练的VOC数据集,在VOC2007_test上的Loss最低也就降到4.36。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. 还想请问一下您训练的学习率是多少,训练多少个epoch?不胜感激! — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

感谢,我再去试试。

@shaoshengsong
Copy link
Owner

It is recommended that git clone this version
https://github.com/shaoshengsong/MobileNetV3-SSD-Compact-Version
loss =1.8,1,9

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