Asymmetric Noise-

[jaideep11061982]

Hi what are optimal values for alpha beta in acse my noise rate is around 0.2 and type asymmetric

[YisenWang]

Hi, which dataset do you use?

[jaideep11061982]

Its a customer dataset 21k images, best accuracy we get 89 on the set

…

On Thu, 18 Feb 2021, 16:27 YisenWang, ***@***.***> wrote: Hi, which dataset do you use? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#10 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AJDFNZCOLAXHAOKTBABNPTLS7TXANANCNFSM4XX2OYHA> .

[YisenWang]

I think you could tune the alpha and beta using grid search to adaptively fit your customer dataset.

…

On 19/02/2021, jaideep11061982 ***@***.***> wrote: Its a customer dataset 21k images, best accuracy we get 89 on the set On Thu, 18 Feb 2021, 16:27 YisenWang, ***@***.***> wrote: > Hi, which dataset do you use? > > — > You are receiving this because you authored the thread. > Reply to this email directly, view it on GitHub > <#10 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AJDFNZCOLAXHAOKTBABNPTLS7TXANANCNFSM4XX2OYHA> > . > -- You are receiving this because you commented. Reply to this email directly or view it on GitHub: #10 (comment)

-- Yisen Wang Department of Computer Science and Technology Tsinghua University Beijing, P.R.China(100084) Email: [email protected] [email protected]

[jaideep11061982]

Ok in general This loss helps prevent noise free label from getting wrong by not letting model overfit to noisy data or helps predicting images which have noisy labels

…

On Thu, 18 Feb 2021, 22:17 YisenWang, ***@***.***> wrote: I think you could tune the alpha and beta using grid search to adaptively fit your customer dataset. On 19/02/2021, jaideep11061982 ***@***.***> wrote: > Its a customer dataset 21k images, best accuracy we get 89 on the set > > On Thu, 18 Feb 2021, 16:27 YisenWang, ***@***.***> wrote: > >> Hi, which dataset do you use? >> >> — >> You are receiving this because you authored the thread. >> Reply to this email directly, view it on GitHub >> < #10 (comment) >, >> or unsubscribe >> < https://github.com/notifications/unsubscribe-auth/AJDFNZCOLAXHAOKTBABNPTLS7TXANANCNFSM4XX2OYHA > >> . >> > > > -- > You are receiving this because you commented. > Reply to this email directly or view it on GitHub: > #10 (comment) -- Yisen Wang Department of Computer Science and Technology Tsinghua University Beijing, P.R.China(100084) Email: ***@***.*** ***@***.*** — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#10 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AJDFNZGY6GCVEOKT5UTY4LTS7VABDANCNFSM4XX2OYHA> .