YoungGod / DFR

Project: Unsupervised Anomaly Segmentation via Deep Feature Reconstruction

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The loss function

renqiqi opened this issue · comments

In training, is the L2 distance used in the loss function and the relevant Euclidean distance not used? Is the experimental result of L2 distance better?
Thanks!