what is the value for L2 regularization coeff, by default,while training?

5 次查看（过去 30 天）

显示更早的评论

krishna Chauhan 2020-10-21

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/621808-what-is-the-value-for-l2-regularization-coeff-by-default-while-training

编辑： Adam Danz 2020-10-27

while trainig a deep learning network in MATLAB, what is the trainingOptions for setting L2 regularization coeff.?

Like if adam optimizer is used how to set this parameter?

more clearly like in optim.Adam in pytorch , weight_decay option is given.how to set it here in MATLAB?

回答（1 个）

Adam Danz 2020-10-21

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/621808-what-is-the-value-for-l2-regularization-coeff-by-default-while-training#answer_520718

I think you're looking for the L2Regularization Solver Option.

6 个评论
显示 4更早的评论隐藏 4更早的评论

krishna Chauhan 2020-10-22

Ya even I was thinking they are same,

for your second suggestion,,,,,,,,,,I m giving same input to both the models but getting entirely different accuaracy. In MATLAB 80% while in Pytorch they got only 50- 55%

though Pytorch has no option for padding='same' may be this is the issue.

I am confused what to do now?

Adam Danz 2020-10-22

编辑：Adam Danz 2020-10-27

If it were me, I'd step through the process in debug mode to study and compare the two methods. Perhaps there's more detail in Matalb's (and PyTorch's) documentation that would shed light on the differences.

Maybe the difference is caused by a small difference in one of the optional parameters, as you mentioned.

请先登录，再进行评论。

请先登录，再回答此问题。