Why estimate sample energy is negative?

Newcomer520 / tf-dagmm

Tensorflow Implementation of dagmm: Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection, Zong et al, 2018

56 stars 17 forks source link

Open QinyuanZhou opened 5 years ago

QinyuanZhou commented 5 years ago

Hello Thank for your great implementation. I just used your code to run, but finding that the sample energy is negative. Can you explain it?

Yuranus commented 4 years ago

I also get the same negative results， maybe the regularization term is large

LuyuanLi97 commented 3 years ago

Hi! Have you solved this problem?