Closed hnyll closed 8 months ago
Anomaly detection can be divided into two subtasks: anomaly classification and segmentation. The anomaly score (i.e. results['pr_sp']
in the test.py) for classification is what you want. BTW, If you're just getting started, I recommend checking relevant papers before reviewing the code; it will greatly aid in understanding. :)
tyty. i will def check out the relevant papers 👍
I want to know if there is a variable/method i can use to score how suspicious/anomalous an image is. im kind of new to this stuff so idk lol