search

lukasruff / Deep-SVDD-PyTorch

A PyTorch implementation of the Deep SVDD anomaly detection method
MIT License
698 stars 197 forks source link

GCN divided by 0 #10

Open ibopeng opened 5 years ago

ibopeng commented 5 years ago

In GCN preporcessing, if a tensor x has the same feature values (e.g., a pixel with RGB = [255, 255, 255]), after mean removal, the L1-norm scale would be equal to 0, which results in 0 / 0. How would you avoid this? Thanks.

liuentong commented 1 year ago

我是这样做的，当0/0时会输出nan，将所有结果的列表输出，再将列表中的nan剔除，重新拍去找到最大和最小