speaker classification loss converge

[Kristopher-Chen]

Hi, how does the speaker classification loss look like on your side? It diverges in the middle of the training process in my experiment. Any idea about how to balance the speaker classification loss for the classification network(positive) and the main network(negative)?

See the training loss curve for speaker classification below. (My network follows the ideas of speaker classification and pitch regression modules, but not the exact one as your task.)

Thank you!

[Chengqi Deng]

I think the loss is reasonable. I've observed similar loss curves.

…

On Fri, Dec 24, 2021 at 10:45 AM Kristopher-Chen ***@***.***> wrote: Hi, how does the speaker classification loss look like on your side? It diverges in the middle of the training process in my experiment. Any idea about how to balance the speaker classification loss for the classification network(positive) and the main network(negative)? See the training loss curve for speaker classification below. (My network follows the ideas of speaker classification and pitch regression modules, but not the exact one as your task.) [image: image] <https://user-images.githubusercontent.com/38187438/147309541-ab6278b9-ba5a-45cb-8c30-06c1de9f01ce.png> Thank you! — Reply to this email directly, view it on GitHub <#4>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AGM2U7BZ23LDFF4P7J3FMXTUSPNDZANCNFSM5KV4BA6Q> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>