How to train net with high class imbalance?
9 ビュー (過去 30 日間)
古いコメントを表示
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 件のコメント
採用された回答
Kenta
2020 年 7 月 11 日
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 件のコメント
その他の回答 (0 件)
参考
カテゴリ
Help Center および File Exchange で Image Data Workflows についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!