How to choose the weigh in imbalanced data?

[kenmikanmi (Kenya Hondoh)]

Hi, equation (1) in this paper computes binary cross entropy as you said.

Also, I found this:

How to Prevent Overfitting

oh if you have class imbalance, use a weighted sampler, so that you see all classes with equal probability. That should help a lot (depending on the severity of your imbalance): http://pytorch.org/docs/data.html#torch.utils.data.sampler.WeightedRandomSampler You can give this to your DataLoader