Open xrli-U opened 3 months ago
Can I understand the settings in the training downstream segmentation network by this way ?
- There are only 500 images per anomlay class for training. But in the paper, per anomaly class has 1000 images.
- An epoch only randomly selects 500 images for training, in which the number of normal images and abnormal images is equal.
- The maximum epoch is 200, but the test data is used to select best_epoch. Is this really allowed when training a model?
Looking forward to your answers. Thank you very much!
Can I understand the settings in the training downstream segmentation network by this way ?
Looking forward to your answers. Thank you very much!