search

pokaxpoka / deep_Mahalanobis_detector

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".
340 stars 78 forks source link

Interpretation of output file #2

Open tayden opened 5 years ago

tayden commented 5 years ago

Could you please add information to the readme about how to interpret the output files? It's not clear what the values in the numpy arrays refer to.

tayden commented 5 years ago

I assume the first n-1 numbers in the array are the Mahalanobis distances for each of the features in features_list, and the nth number is an inlier/outlier label.