search

wutong16 / DistributionBalancedLoss

[ ECCV 2020 Spotlight ] Pytorch implementation for "Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets"
362 stars 46 forks source link

Question regarding the model #3

Closed nurmanmus closed 4 years ago

nurmanmus commented 4 years ago

this model trains images. Can it be used to train numerical training data to do a multi-label classification problem?

wutong16 commented 4 years ago

Hi @nurmanmus!

We haven't tried the model on other forms of data yet. The feature extractor could be different, but I guess the weights and regularization in the classifier can be adapted to the new task.