Learning-Deep-Features-for-One-Class-Classification icon indicating copy to clipboard operation
Learning-Deep-Features-for-One-Class-Classification copied to clipboard

Published 20 hours ago • verified publisher icon buiduchanh

data.py: why "x_train_s" and "x_ref" are identical?

Open nhatami opened this issue 5 years ago • 1 comments

Hi,

Thanks for the code.

In data.py file:

x_train_s.append(cp1) x_ref.append(cp1)

shouldn't x_train_s and x_ref be different? or I am missing something?

Thanks

nhatami avatar Nov 15 '19 14:11 nhatami

Should be different, yes ! You can use any image dataset ! It is used to compute descriptiveness loss ! There is an error in this code

"An external multi-class reference dataset is used to evaluate the descriptiveness loss."

See the original paper

Sylv-Lej avatar Jul 22 '20 13:07 Sylv-Lej