How to judge whether the prediction result is OK or ng

marco-rudolph / differnet

This is the official repository to the WACV 2021 paper "Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows" by Marco Rudolph, Bastian Wandt and Bodo Rosenhahn.

215 stars 67 forks source link

How to judge whether the prediction result is OK or ng #7

Closed machine52vision closed 3 years ago

machine52vision commented 3 years ago

How to judge whether the prediction result is OK or ng，and where is the threshold set？

marco-rudolph commented 3 years ago

See here.

I would say the choice of theta could vary for different datasets. One could have a validation set of non-anomalies to estimate which threshold should be chosen for a specific target false positive rate.