Open lightwithshadow opened 5 years ago
Hi,
I think 5000epoch are quite large, thus overfitting may be occurring. Code includes tensorboard as "--tensorboard_log_dir". I don’t know the database what you use, but when validation set inferences, learning rate and training epoch can be adjusted by checking the MSE curve. For VCC2016 database, I will update the learning curve.
Cheers, Wonjin
Hi,
Thanks for your reply! I will try it again. Thanks for your attention to this matter.
Cheers, shadow
------------------ 原始邮件 ------------------ 发件人: "Wonjin, Jung"<notifications@github.com>; 发送时间: 2019年9月23日(星期一) 中午1:25 收件人: "onejiin/CycleGAN-VC2"<CycleGAN-VC2@noreply.github.com>; 抄送: "1101174181"<1101174181@qq.com>;"Author"<author@noreply.github.com>; 主题: Re: [onejiin/CycleGAN-VC2] Is epoch = 5000 too large? (#3)
Hi,
I think 5000epoch are quite large, thus overfitting may be occurring. Code includes tensorboard as "--tensorboard_log_dir". I don’t know the database what you use, but when validation set inferences, learning rate and training epoch can be adjusted by checking the MSE curve. For VCC2016 database, I will update the learning curve.
Cheers, Wonjin
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.
Thank you for your contribution to this project. When I was running demo, an epoch take about 30 minutes. Is epoch = 5000 too large? Looking forward to your reply! Thanks!!!