How to train net with high class imbalance?
13 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Carlos Loredo López-Morago
le 11 Juil 2019
Réponse apportée : Kenta
le 11 Juil 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 commentaires
Réponse acceptée
Kenta
le 11 Juil 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 commentaires
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Image Data Workflows dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!