search

liznerski / fcdd

Repository for the Explainable Deep One-Class Classification paper
MIT License
225 stars 62 forks source link

how to generate ground truth map #56

Closed Se0ngYe0l closed 1 year ago

Se0ngYe0l commented 1 year ago

I want to train using a custom dataset.

  1. python run_custom.py -gtms --supervise-mode other

datasets/custom/test/class1/normal/
datasets/custom/test/class1/anomalous/

datasets/custom/train/class1/normal/
datasets/custom/train/class1/anomalous/

Skipped computing the gtmap ROC score. for some samples no ground-truth maps were found

  1. run_prediction_with_snapshot.py image
liznerski commented 1 year ago

It seems that the trainer's logger is a string instead of a Logger instance. Did you have a typo in line 72? For example, did you write logger = "fcdd/data/results/foo" instead of logger = Logger("fcdd/data/results/foo")?