Info
Diese Frage ist geschlossen. Öffnen Sie sie erneut, um sie zu bearbeiten oder zu beantworten.
How to identify when an Image classifier is passed an image which fits poorly with all classification labels
2 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
I've retrained AlexNet to identify images corresponding to 3 different classes. I'd like to obtain a confidence measure for the predictions, and to identify when the image being classified doesn't correspond to any of the classes well. I'm new to this area, so any tips, pointers would be greatly appreciated, thanks.
0 Kommentare
Antworten (0)
Diese Frage ist geschlossen.
Siehe auch
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!