Closed kcharanj closed 4 years ago
The code is available. Often the number of outliers in the batch are twice that of the in-distribution points, so the ratio is often 2 outliers for every in-distribution example.
On Tue, Feb 4, 2020 at 9:14 AM Charanjit Kaur Khosa < notifications@github.com> wrote:
Hi, Could you please let me know the proportion of "in-distribution" and OOD data points in the training sample? Thanks
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/hendrycks/outlier-exposure/issues/8?email_source=notifications&email_token=ACZBITXBU3DZA6JZIKTA5WLRBGO57A5CNFSM4KP2WSOKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4IK6Z5DA, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACZBITSRECDGWRGG5LFAMZ3RBGO57ANCNFSM4KP2WSOA .
okay, thank you.
Hi, Could you please let me know the proportion of "in-distribution" and OOD data points in the training sample? Thanks