How to train net with high class imbalance?
13 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Carlos Loredo López-Morago
am 11 Jul. 2019
Beantwortet: Kenta
am 11 Jul. 2020
Hi, I am doing a semantic segmentation that has a large difference between the two classes. So that, it tends to overpredict when I train the network. Is there any way to train the network specifically in one of the classes?
I am using classweights already, but as most of the pictures is background, the training accuracy tends to increase and the loss to decrease until constant, which generates zero accuracy when testing in the most important but imbalanced class.
0 Kommentare
Akzeptierte Antwort
Kenta
am 11 Jul. 2020
Over-sampling can be one solution for that task. Copy the image of smaller classes so that the number of images in each class can balance and perform training using data augmentation function.
0 Kommentare
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Image Data Workflows finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!