search

GilLevi / AgeGenderDeepLearning

628 stars 284 forks source link

Unbalanced accuracy among folds? #24

Closed FlatErik90 closed 6 years ago

FlatErik90 commented 6 years ago

Hi, I'm experimenting with my own CNN for age recognition and I'm wondering whether it is normal to get very different validation accuracy values for the different folds? For example, I get: Fold 0 as test set: 55% Fold 1 as test set: 38% Fold 2 as test set: 50% Fold 3 as test set: 44% Fold 4 as test set: 47%

Is it normal to get such unbalanced results? Or could it be a bug in my data loading code since I'm not using any of your code so far.

Thanks a lot!

GilLevi commented 6 years ago

Hi,

Thank you for your interest in our work. The accuracy on fold 1 seems a bit strange, but other than than it's seem reasonable. Here are the results I reached on the different folds:

Fold 0 as test set: 54% Fold 1 as test set: 44% Fold 2 as test set: 54% Fold 3 as test set: 46% Fold 4 as test set: 49%

Best, Gil