This is the official repository to the WACV 2022 paper "Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection" by Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn and Bastian Wandt.
If the starting epoch of the training is different from 0, Score_Observer throws an error. This can be problematic if we want to resume training. This simple fix makes Score_Observer independent from the number of the starting epoch
If the starting epoch of the training is different from 0, Score_Observer throws an error. This can be problematic if we want to resume training. This simple fix makes Score_Observer independent from the number of the starting epoch