Weighted learning

1

Do anyone know how can I do weighted learning(e.g.In sklean.svm.svc ,the parameter ‘class_weight’ allow you to assign different weight to different class ) in CNN with cross entropy loss?Thanks very much!

2

Just pass the weights as an argument to torch.nn.CrossEntropyLoss

2 Likes
3

Are the weights simply the proportion of cases in each class? Or is it the inverse of this?

4 Likes
4

I am on the same boat. Don’t know what weights to put.

5

Hi All,

Did you get any update on this? Is there any sample code for this?

Thanks