over-fitting
WillLiGitHub opened this issue · comments
when you train multi-labels classification on you dataset,
whether there is serious overfitting?
whether you novel loss function can resolve this problem?
Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet
WillLiGitHub opened this issue · comments
when you train multi-labels classification on you dataset,
whether there is serious overfitting?
whether you novel loss function can resolve this problem?